JP6721732B2 - Speech recognition device, speech recognition method, and speech recognition program - Google Patents

Description

The present invention relates to a voice recognition device, a voice recognition method, and a voice recognition program.

Conventionally, in Internet browsers, smart TVs, tablets, and smartphone terminals, the voice uttered by the user is compressed by the terminal (hereinafter also referred to as the client) and sent to the cloud side as it is, and the voice on the cloud side system is used. Speech recognition is performed using a cloud-type speech recognition system in which recognition processing is performed and the result is received and used by a terminal side via a network. In addition, a cloud-type speech recognition system using a method called DSR (Distributed Speech Recognition) in which only the acoustic analysis is performed on the terminal, only the feature amount is transmitted, and the speech is recognized on the cloud side, is used without compressing and directly transmitting to the cloud side. Voice recognition is also performed.

There is also a technology in which an HTML5 browser is used to acquire voice with a web application, send compressed voice to the cloud side via websocket communication, perform voice recognition on the cloud side, and use the result on a terminal. (See, for example, Non-Patent Document 1).

With these mechanisms, abundant CPU resources and statistical data on the cloud side are used to perform background noise removal, separation of speech and non-speech sections by sound pressure and acoustic models, phoneme analysis, and statistical analysis by language models. It is possible to perform voice recognition with accuracy. Further, in recent years, a speech recognition method that uses deep learning technology to combine CPU and GPU resources to make each processing more accurate, and uses deep learning technology to form an integrated model that directly converts acoustic features into sentences. Is also proposed.

Furthermore, by increasing the accuracy of the language model every day by increasing the weight of big data obtained on the cloud side, for example, new words, buzzwords, words that are frequently used by current users such as current affairs words, etc. We are able to perform accurate and practical voice recognition.

As conventional techniques for improving the accuracy of voice recognition, for example, the following (1) to (3) can be mentioned, but each has the following problems.

(1) Echo canceller When a signal reproduced by a speaker is picked up by a microphone and a loop is formed in which the picked-up acoustic signal is included in the signal reproduced by the speaker, echo or howling occurs. .. An echo canceller is a conventional technique for removing and reducing the echo and howling. The echo canceller is used to reduce the echo and howling.By performing a filtering process that removes the acoustic signal output from the speaker immediately before from the acoustic signal obtained by the microphone, the echo and howling effects Is a technology except. However, when a plurality of independent devices are combined and different speakers are present, such as in a living room at home, it is not possible to remove/reduce the voice sound flowing from other speaker devices by an echo canceller. Also, even if audio is sent directly to the cloud from a smartphone application or Web API, the audio of the video is output directly from the video playback application, which is another application, and the audio signal to be canceled is sent from another application or the API side. Is difficult to understand and cannot be removed or reduced by an echo canceller.

(2) Difference in Sound Pressure As a conventional technique for distinguishing a background voice from a voice uttered by a speaker into a microphone, there is a method of utilizing a difference in sound pressure, that is, the power of an acoustic signal. However, when the playback volume of TV or radio is high, the speaker of TV or radio is close to the microphone, or the microphone and the speaker are far apart from each other, there is a large difference in the sound pressure between the background sound and the sound of the speaker. In some cases, the background voice and the voice of the speaker cannot be discriminated well because there is no.

(3) Separation by acoustic model As a conventional technology for separating human voice from environmental noise such as air conditioning sound and engine sound, there is a sound source separation technology that focuses on the difference in the generation model of the sound of the generation source. Further, in recent years, a sound source separation technique based on advanced feature amount determination using deep learning has been developed, and the accuracy of sound source separation has been rapidly improved (for example, see Non-Patent Document 2). However, live broadcasting TV radio, guide broadcasting, etc. are “human voices” themselves, so if the playback quality of the audio device that plays back the broadcast audio is high, or if the playback volume is high, , The background voice and the voice of the speaker may not be sufficiently separated.

[Online], [October 13, 2015 search], Internet <http://www.ntt.co.jp/news2014/1409/140911a.html> [Online], [October 15, 2015 search], Internet <http://www.ntt.co.jp/journal/1509/files/jn201509017.pdf>

However, if there is a relatively loud sound in the background of the voice that the speaker wants to recognize, in addition to the acoustic signal of the voice made by the speaker, the acoustic signal targeted for voice recognition has a background. Since the acoustic signal of the voice is also included, the speech recognition result of the background acoustic signal that the speaker does not intend is included in the speech recognition result, and the speech recognition result different from the speech recognition result desired by the speaker is generated. There is a problem that it will be obtained.

For example, when a TV or radio broadcast is constantly playing at a relatively loud volume in the background where a voice to be recognized is emitted, a voice sound (announcement) output from these TV or radio speakers during the recognition period of the voice recognition. (Serifs) are mixed unintentionally and may not be recognized correctly (Problem 1).

Also, when performing voice recognition on acoustic signals picked up in environments where guidance broadcasts or in-building broadcasts are frequently loud, such as outdoor stadiums, lecture halls, public viewing venues, and inside trains, voice recognition is performed. There is also a problem that voice sounds (announcements and dialogues) of guide broadcasts and in-house broadcasts are included in the middle of the identification period, and those voice recognition results are unintentionally mixed with the voice search results (Problem 2).

In addition, when playing a recorded movie or playing a VOD while downloading, in the case where the voice of the app that is playing the video and the voice recognition app individually operate in multitask, the recognition of the voice recognition is performed. There is also a problem that the voice sound (announcement or dialogue) of the video is unintentionally mixed in the voice recognition result during the period (problem 3).

The present invention has been made in view of the above circumstances, and recognizes an input acoustic signal including a voice of a speaker to obtain a recognition result, and also recognizes another input acoustic signal. To reduce the possibility of including unnecessary speech recognition results by obtaining the recognition results and removing the common ones from these recognition results from the speech recognition results of the acoustic signal containing the speech of the input speaker. It is an object of the present invention to provide a voice recognition device, a voice recognition method, and a voice recognition program capable of improving the voice recognition rate of a speaker's voice.

In order to solve the above problems, the present invention voice-recognizes an input acoustic signal including a voice of a speaker to obtain a recognition result, and also voice-recognizes a broadcast acoustic signal of a public broadcast serving as a reception target area. An identification result is obtained, and a common one of these recognition results is removed from the voice recognition result of the acoustic signal including the voice of the input speaker.

One embodiment of the present invention is obtained from a public broadcasting station connected according to an Internet connection protocol, and a first acoustic signal which is an acoustic signal picked up by a first sound pickup unit including a voice of a first speaker. 1st or more broadcast acoustic signal to Mth broadcast acoustic signal (M is an integer of 1 or more) which are the acoustic signals of one or more broadcasts that have been performed, and speech recognition is performed for each acoustic signal, and speech recognition is performed for each acoustic signal. First voice recognition result and first broadcast voice recognition result-voice recognition means for obtaining Mth broadcast voice recognition result, and at least one voice recognition of the first broadcast voice recognition result to the Mth broadcast voice recognition result. The partial voice recognition result included in the result and the partial voice recognition result included in the first voice recognition result have the same partial voice recognition result, and the partial voice corresponding to the acoustic signal at substantially the same time. And a speech recognition result processing unit that obtains, when the recognition result is the partial speech recognition result, the result obtained by deleting the partial speech recognition result from the first speech recognition result as the speech recognition result of the first speaker. is there.

According to one aspect of the present invention, a voice recognition result of the first voice signal is obtained by voice-recognizing a first voice signal, which is a voice signal including the voice of the first speaker by the first voice collecting unit. And the first broadcast acoustic signal to the Mth broadcast acoustic signal (M is 1) that is the acoustic signal of one or more broadcasts received by the receiver installed in the receiving area of the public broadcast signal. Speech recognition to obtain, via a network, a first broadcast sound signal to a first broadcast sound recognition result, which is a sound recognition result of the Mth broadcast sound signal, through a network. Means, and a partial voice recognition result included in at least one or more voice recognition results of the first broadcast sound recognition result to the Mth broadcast sound recognition result in which the first sound collecting means is in the broadcast receiving area. When the partial voice recognition result included in the first voice recognition result has the same content of the partial voice recognition result and is the partial voice recognition result corresponding to the acoustic signals at substantially the same time, the partial voice A voice recognition device including a voice recognition result processing unit that obtains a result obtained by deleting a recognition result from the first voice recognition result as a voice recognition result of the first speaker.

According to one aspect of the present invention, voice recognition is performed on a first acoustic signal, which is an acoustic signal including a voice of a first speaker, by a first sound collecting unit included in a client device used by a user. The first voice recognition result, which is the voice recognition result of the first acoustic signal, and the one or more broadcasts received by the cloud device installed in the receiving area of the public broadcast signal and connected to the client device via the network. First broadcast sound signal which is a sound signal to Mth broadcast sound signal (M is an integer of 1 or more) is speech-recognized, and first broadcast sound signal is a sound recognition result of the first broadcast sound signal to the Mth broadcast sound signal. And a voice recognition unit for obtaining a result-the M-th broadcast voice recognition result, and at least one of the first broadcast voice recognition result-the M-th broadcast voice recognition result, in which the first sound collecting unit is in a broadcast receiving area. The partial voice recognition result included in the above voice recognition result and the partial voice recognition result included in the first voice recognition result have the same content of the partial voice recognition result, and are converted into acoustic signals at substantially the same time. Voice recognition result processing means for obtaining a result obtained by deleting the partial voice recognition result from the first voice recognition result as a voice recognition result of the first speaker when the corresponding partial voice recognition result is obtained. It is a voice recognition device.

One aspect of the present invention is the above-described voice recognition device, wherein the voice recognition result processing means includes partial voices included in at least one voice recognition result of the first broadcast voice recognition result to the Mth voice recognition result. The recognition result and the partial voice recognition result included in the first voice recognition result have the same partial voice recognition result and are partial voice recognition results corresponding to acoustic signals at substantially the same time. Only for a plurality of the first to the Mth broadcast voice recognition results, the contents of the partial voice recognition result are the same in the voice recognition result and the partial voice recognition result included in the first voice recognition result. Yes, all partial speech recognition results corresponding to acoustic signals at approximately the same time are obtained, and the obtained partial speech recognition result is deleted from the first speech recognition result. Get as a result.

According to one aspect of the present invention, the voice recognition device is connected to a first acoustic signal, which is an acoustic signal collected by the first sound collecting unit including the voice of the first speaker, according to the Internet connection protocol. The sound signals of the first broadcast sound signal to the Mth broadcast sound signal (M is an integer of 1 or more), which are the sound signals of one or more broadcasts acquired from the public broadcasting station, are recognized by voice, and A first voice recognition result and a first broadcast voice recognition result, which are voice recognition results for the acoustic signal, a voice recognition step of obtaining a Mth broadcast voice recognition result, and the voice recognition device uses the first broadcast voice recognition result to the Mth broadcast. The partial voice recognition result included in at least one voice recognition result of the voice recognition results and the partial voice recognition result included in the first voice recognition result have the same content of the partial voice recognition result, and When the partial speech recognition result corresponding to the acoustic signal at the same time is obtained, the partial speech recognition result obtained by deleting the partial speech recognition result from the first speech recognition result is obtained as the speech recognition result of the first speaker. And a voice recognition method including steps.

According to one aspect of the present invention, the voice recognition device performs voice recognition of a first acoustic signal, which is an acoustic signal collected by the first sound collecting unit including the voice of the first speaker, to obtain a first sound. The first speech recognition result which is the speech recognition result of the signal, and the first broadcasting sound signal to the Mth broadcasting sound which are the sound signals of one or more broadcasts received by the receiver installed in the area where the public broadcasting signal is received. A signal (M is an integer of 1 or more) is voice-recognized, and a first broadcast sound signal to a first broadcast sound recognition result, which is a sound recognition result of the M-th broadcast sound signal, to a M-th broadcast sound recognition result are connected to a network. And a voice recognition device, wherein the voice recognition device obtains at least one voice recognition result from the first broadcast voice recognition result to the Mth broadcast voice recognition result in which the first sound collecting unit is in a broadcast receiving area. The partial voice recognition result included in the result and the partial voice recognition result included in the first voice recognition result have the same partial voice recognition result, and the partial voice corresponding to the acoustic signal at substantially the same time. And a speech recognition result processing step of obtaining a result obtained by deleting the partial speech recognition result from the first speech recognition result as a speech recognition result of the first speaker when the recognition result is a recognition result. ..

One aspect of the present invention is a first acoustic signal, which is a sound signal picked up by a voice recognition device including a voice of a first speaker by a first sound pickup means included in a client device used by a user. Is received by a cloud device that is installed in the receiving area of the public broadcast signal and is connected to the client device via a network. It is a voice recognition result of the first broadcast acoustic signal to the Mth broadcast acoustic signal by voice-recognizing the first broadcast acoustic signal to the Mth broadcast acoustic signal (M is an integer of 1 or more) which are the one or more broadcast acoustic signals. A voice recognition step of obtaining a first broadcast voice recognition result to an Mth broadcast voice recognition result; and a voice recognition device, wherein the first sound collecting means is included in the first broadcast voice recognition result to the Mth broadcast voice recognition result. The partial voice recognition result included in the at least one voice recognition result in the broadcast receiving area and the partial voice recognition result included in the first voice recognition result have the same partial voice recognition result. , And the partial speech recognition result corresponding to the acoustic signals at approximately the same time, the partial speech recognition result obtained by deleting the partial speech recognition result from the first speech recognition result is obtained as the speech recognition result of the first speaker. And a voice recognition result processing step.

One aspect of the present invention is a voice recognition program for causing a computer to operate as the above voice recognition device.

According to the present invention, an unnecessary voice recognition result is included by removing a part common to the voice recognition result of another input audio signal from the voice recognition result of the input voice signal of the speaker. By reducing the possibility of being generated, it is possible to improve the voice recognition rate for the voice of the speaker.

It is a block diagram which shows the structure of the whole system containing the speech recognition system of 1st, 3rd embodiment of this invention. It is a block diagram which shows the structure by one client side apparatus and cloud side apparatus of the speech recognition system of 1st Embodiment of this invention. It is a figure which shows the flow of a process of the speech recognition result processing part of the 1st operation example of 1st Embodiment of this invention. It is a figure for demonstrating the specific example of the speech recognition result processing part of the 1st operation example of 1st Embodiment of this invention. It is a figure for demonstrating the specific example of the speech recognition result process part of the 2nd operation example of 1st Embodiment of this invention. It is a figure for demonstrating the specific example of the speech recognition result processing part of the 3rd operation example of 1st Embodiment of this invention. It is a figure which shows the flow of a process of the speech recognition result processing part of the 4th operation example of 1st Embodiment of this invention. It is a figure which shows the flow of a process of the modification of the speech recognition result processing part of the 4th operation example of 1st Embodiment of this invention. It is a figure which shows the flow of a process of the speech recognition result processing part of the 6th operation example of 1st Embodiment of this invention. It is a block diagram which shows the structure of the whole system containing the speech recognition system of 2nd Embodiment of this invention. It is a block diagram which shows the component part by one client side apparatus and cloud side apparatus of the speech recognition system of 2nd Embodiment of this invention. It is a figure which shows the flow of a process of the speech recognition result processing part of the 1st operation example of 2nd Embodiment of this invention. It is a figure for demonstrating the specific example of the speech recognition result processing part of the 1st operation example of 2nd Embodiment of this invention. It is a figure which shows the flow of a process of the speech recognition result processing part of the 3rd operation example of 2nd Embodiment of this invention. It is a block diagram which shows the component part by one client side apparatus and cloud side apparatus of 3rd Embodiment of this invention. It is a figure which shows the flow of a process of the speech recognition result processing part of 3rd Embodiment of this invention. It is a block diagram which shows the component part by one client side apparatus and cloud side apparatus of 4th Embodiment of this invention. It is a block diagram which shows the component by one client side apparatus and cloud side apparatus of the modification of 4th Embodiment of this invention. It is a figure for demonstrating the specific example of the speech recognition result processing part of the modification of 4th Embodiment of this invention. It is a block diagram which shows the structure of the speech recognition apparatus of this invention.

Hereinafter, a voice recognition system according to an exemplary embodiment of the present invention will be described with reference to the drawings.

Here, a usage pattern assumed by the present invention will be described. The present invention is not limited to the case in which the voice recognition microphone and the speaker are close to each other, but is assumed to be used in the case of a relatively long distance, specifically, a case of a relatively long distance of about 45 cm to several meters. ..

Assuming surrounding conditions, voice sounds (announcements and dialogues) of TV broadcasts and radio broadcasts outside this system are flowing at intervals of a few seconds to a dozen seconds, and guide broadcasts are played irregularly during the recognition period. This is the case, for example, when voice sounds of TV, radio, guide broadcasting, etc., enter the audio signal input to the client side device irregularly.

<First Embodiment>
First, as the first embodiment of the present invention, the result of voice recognition of an acoustic signal including the voice of a speaker input to a client-side device is the same as the result of voice recognition of an acoustic signal input to another client-side device. The form of removing a part will be described. FIG. 1 is a block diagram showing the configuration of the voice recognition system in the first embodiment. In the figure, reference numeral 100 is a voice recognition system, reference numerals 1 ₁ to 1 _N are a plurality of (N, N is an integer of 2 or more) client side devices, and reference numeral 2 is a cloud side device. The client-side devices 1 ₁ to 1 _N are devices used by users, and include, for example, smartphones, smart TVs, HDMI (trademark) dongle STB (“STB” is a “set top box”), small STBs, and advanced home appliances. Devices, game consoles, etc. The cloud side device 2 is connected to the client side devices 1 ₁ to 1 _N via the network 3. The network 3 is for allowing the client side devices 1 ₁ to 1 _N of the voice recognition system 100 and the cloud side device 2 to transmit and receive information according to the connection protocol of the Internet, and is, for example, the Internet. The minimum configuration included in each of the client side devices 1 ₁ to 1 _N is the same, and therefore, in the following description, a part of the voice recognition system 100 according to the first embodiment that is configured by the client side device 1 ₁ and the cloud side device 2. Will be described with reference to FIG. 2, which is a detailed block diagram.

Client device _{1 1} includes an audio input unit 11 _1, the user information acquiring unit 12 _1, the audio output unit 13 _1, the search result receiving unit 14 _1, configured to include at least the screen display unit 15 _1.

The cloud side device 2 includes at least a voice receiving unit 21, a voice recognizing unit 22, a voice recognition result holding unit 23, a voice recognition result processing unit 24, a search processing unit 25, and a search result transmitting unit 26.

Next, the operation of the voice recognition system of the first embodiment will be described.

[[First Operation Example of First Embodiment]]
As a first operation example, a sentence in which each of the _first to _Nth users uses the client side devices 1 ₁ to 1 _N and the first user wants to obtain a search result for the client side device 1 ₁ the speaks, an example of operation of displaying a search result corresponding to the utterance to the client-side apparatus 1 ₁ of the screen display unit 15 _1. Here, as a more specific case, N=3, and the first user is in a place where the sound of TV or radio is played or the guide broadcast such as a station or a department store is played irregularly. There is a second user in the same TV, radio, or guide broadcast as the first user, and the same TV, radio, or guide broadcast as the first user does not flow, and there is a different environmental sound. A case where there is a third user will be described as an example.

Client device 1 ₁ of the speech input unit 11 ₁ obtains an acoustic signal emitted around the client-side apparatus 1 _1, and outputs the acquired audio signal to the audio transmission unit 13 _1. If the first user has uttered a sentence to be obtained search results to the client-side apparatus 1 _1, obtains and outputs a sound signal including a voice first user uttered. If the client-side apparatus 1 ₁ of environmental sounds such as a television or radio or announcement around has occurred, and outputs the acquired audio signal including the ambient sound. Therefore, in the above specific case, an acoustic signal composed of the voice uttered by the first user, the sound of the television or the radio, and the environmental sound of the guide broadcast is acquired and output.

User information acquisition section 12 ₁ of the client-side apparatus 1 ₁ obtains the time information voice input unit 11 ₁ of the client-side apparatus 1 ₁ acquires the audio signal, which can specify the time information and the client-side apparatus 1 ₁ identification information (hereinafter, referred to as "ID") to the audio transmission unit 13 ₁ and the user information. The time information, for example, absolute time, for example, if the client-side apparatus 1 ₁ is a smart phone with a built-in GPS receiver, the GPS receiver when the smartphone microphone is a voice input unit 11 ₁ obtains a sound signal The absolute time received by the department may be used as the time information. Further, for example, it may be time information obtained from a base station of the mobile carrier network or a communication server, or may be time information of a local clock held by the OS of the smartphone. In the first embodiment, the time information is used by the voice recognition result processing unit 23 to specify whether or not the times at which the acoustic signals acquired by each of the plurality of client side devices are emitted are the same. Since this is a mere fact, the absolute time itself does not have to be the absolute time as long as the time is common to a plurality of client side devices.

Voice output unit 13 ₁ of the client-side apparatus 1 ₁ sends a transmission signal including the user information acoustic signal and the user information acquisition section 12 ₁ speech input unit 11 ₁ is output is output to the cloud side device 2 .. To be more precise, the voice transmitting unit 13 ₁ transmits the transmission signal including the acoustic signal output by the voice input unit 11 ₁ and the user information output by the user information acquiring unit 12 ₁ to the cloud side device 2 in order to transmit the transmission signal to the cloud side device 2. Send to 3. The transmission of the transmission signal is performed, for example, every predetermined time period such as 10 ms. The audio output unit 13 ₁ obtains a code string acoustic signal is encoded by a predetermined encoding method, it may be sent a transmission signal including a resultant code sequence and the user information. The audio output unit 13 ₁ performs such feature extraction, which is part of the processing of the speech recognition process on the acoustic signals, sends a transmission signal including a feature amount and the user information obtained by the process May be. Since there are many known technologies and well-known technologies in the technology of sending a transmission signal to another device via a network and the technology of distributing the voice recognition processing in the client side device and the cloud side device, The description is omitted.

Client device ₁ 2 to 1 _N audio input unit ₁₁ 2 to 11 _N, the user information acquiring unit ₁₂ 2 to 12 _N and the voice sending section ₁₃ 2 to 13 _N be respectively client device _{1 1} of the speech input unit 11 ₁ , the same operation as the user information acquisition unit 12 ₁ and the voice transmission unit 13 ₁ . Therefore, if the above specific case, the client-side apparatus 1 _2, and audio second user has uttered, the same environment sound and the first user, to obtain a composed audio signal by, A transmission signal including the acoustic signal and user information is transmitted. Moreover, the client-side apparatus 1 _3, and audio third user has uttered, and different environmental sound from the first user, to obtain a composed acoustic signal by a corresponding acoustic signal and the user information The transmission signal including is transmitted.

The voice receiving unit 21 of the cloud side device 2 receives the transmission signals transmitted by the voice transmitting units 13 _{1 to} 13 _N of the client side devices 1 ₁ to 1 _N , respectively, and receives the acoustic signal and the user signal from the respective received transmission signals. Take out a set of information and output it. The reception of the transmission signal is performed, for example, every predetermined time period such as 10 ms. When the voice sending units 13 _{1 to} 13 _N code the acoustic signal by a predetermined coding method to obtain a code string and send a transmission signal including the obtained code string, the voice reception of the cloud side device 2 is performed. The unit 21 obtains an acoustic signal by decoding a code string included in the received transmission signal by a decoding method corresponding to a predetermined encoding method, and outputs a set of the obtained acoustic signal and user information. Good. In addition, the voice sending units 13 _{1 to} 13 _N perform feature amount extraction, which is a part of the voice recognition process, on the acoustic signal, and transmit a transmission signal including the feature amount and user information obtained by the process. In the case of sending, the feature amount may be extracted from the transmission signal instead of the acoustic signal, and the set of the extracted feature amount and user information may be output.

The voice recognition unit 22 of the cloud-side device 2 performs voice recognition processing on each acoustic signal output by the voice reception unit 21, and obtains a voice recognition result that is a character string corresponding to the voice included in the acoustic signal. , A pair of a voice recognition result, time information corresponding to the voice recognition result, and an ID corresponding to the voice recognition result is output. If there is no time information or an inappropriate value, the received time information may not be used, and the server may manage the data based on the approximate time information.

The voice recognition process is performed for each predetermined group of acoustic signals. For example, the voice recognition unit 22 sequentially stores the acoustic signals output by the voice reception unit 21 in a storage unit (not illustrated) in the voice recognition unit 22, and performs utterance period detection on the stored acoustic signals to detect each utterance period. Of the acoustic signal is obtained, and voice recognition processing is performed on the group of acoustic signals for each utterance section to obtain a voice recognition result which is a character string for the group of acoustic signals for each utterance section. In addition, for example, the voice recognition unit 22 may perform voice recognition processing on a group of acoustic signals in a plurality of utterance sections to obtain a voice recognition result that is a character string for a group of acoustic signals in a plurality of utterance sections. Good.

Therefore, if the above specific case, the speech recognition unit 22, as a speech recognition result to the client-side apparatus 1 ₁ of the acoustic signal, the first user utterance was such as voice and TV or radio or announcement Environment A character string consisting of a sound and a voice recognition result is obtained. The speech recognition unit 22, as a speech recognition result to the client-side apparatus 1 _second acoustic signal consists of a speech recognition result of the second user utterance voice and the same environment sound and the first user character Get the columns. The speech recognition unit 22, as a speech recognition result to the client-side apparatus 1 _third acoustic signal from a sound third user has uttered the first user and the speech recognition result of the different environmental sound To get the string.

A known voice recognition technique may be used for the voice recognition process. That is, as the details of the voice recognition processing such as the acoustic model, the language model, and how to obtain the feature amount, a publicly known one may be used. Further, as the voice recognition process, an integrated voice recognition process using deep learning may be used. In these voice recognition processes, the voice signal may be recognized after the acoustic signal is analyzed by a not-shown analysis unit or the like so as to be in a prescribed section. When the voice receiving unit 21 outputs the feature amount instead of the acoustic signal, the voice recognizing unit 22 may perform the voice recognition process using the feature amount. In any case, since there are many publicly known techniques and well-known techniques in the voice recognition process itself, detailed description will be omitted.

Since the voice recognition processing is performed for each predetermined group of acoustic signals, the character string of the voice recognition result corresponds to the predetermined group of acoustic signals. Therefore, for example, the voice recognition unit 22 obtains the representative time from the time information included in the plurality of user information corresponding to the predetermined set of acoustic signals subjected to the voice recognition process, and obtains the time information indicating the representative time. Pair with the voice recognition result. The representative time may be one that represents the time when the acoustic signal corresponding to the character string of the voice recognition result is emitted. For example, the start time at which the character string of the voice recognition result is emitted may be set as the representative time. Further, a plurality of representative times may be included in one voice recognition result. For example, for each partial character string such as a word included in the speech recognition result, the time at which the word or the like is emitted may be set as the representative time.

The ID paired with the voice recognition result is included in the user information input from the voice receiving unit 21 in combination with the ID corresponding to the voice recognition result, that is, the acoustic signal from which the voice recognition result is obtained. This is the ID that will be sent.

The voice recognition result holding unit 23 of the cloud side device 2 stores the set of the voice recognition result, the time information, and the ID output by the voice recognition unit 22. The contents stored in the voice recognition result holding unit 23 include a process in which the voice recognition result processing unit 24 determines whether there is a partial character string such as a word having a common time, and a partial character string such as a word having a common time. It is used for a process of removing a speech recognition result from the speech recognition result to obtain a processed speech recognition result. Therefore, the voice recognition result holding unit 23 stores the set of the voice recognition result output by the voice recognition unit 22, the time information, and the ID for the time required by the voice recognition result processing unit 24. Further, the stored contents held in the voice recognition result holding unit 23 may be deleted when the processing of the voice recognition result processing unit 24 using the stored contents is finished.

The voice recognition result processing unit 24 of the cloud-side device 2 includes a part of the character string of the voice recognition result of at least one set of voice recognition result, time information, and ID stored in the voice recognition result holding unit 23. For each character string, if there is a match between the substring and the time among other pairs of speech recognition result, time information, and ID, remove the matching substring. The processed voice recognition result is output, and the processed voice recognition result and the ID are combined and output. Therefore, the processed voice recognition result for at least one client-side device is output. It should be noted that in determining whether the times match, it may be determined that they are the same time in consideration of an error in absolute time in each client side device, an error in time in voice recognition processing, and the like. That is, for at least one processing target client side device, if another client side device has the same partial character string (common partial character string) as the processing target client side device at approximately the same time, The processed character recognition result is obtained by removing the common partial character string from the character string of the voice recognition result of the processing target client side device.

It should be noted that this process may be performed on all of the other client side devices, or may be performed on at least one of the other client side devices. In this case, only the voice recognition result necessary for the processing of the voice recognition result processing section 24 may be obtained in the previous stage. That is, the operations of the voice receiving unit 21, the voice recognition unit 22, and the voice recognition result holding unit 23 for obtaining the voice recognition result unnecessary for the processing of the voice recognition result processing unit 24 may be omitted.

Here, in the above example of N = 3, it will be described with reference to FIGS. 3 and 4 for example at least some one client device is a client-side apparatus 1 _1. FIG. 3 is a diagram illustrating a processing flow of the voice recognition result processing unit 24 in this operation example, and FIG. 4 is a diagram illustrating an example of a voice recognition result and a processed voice recognition result in this example. The example of FIG. 3, the subject of each of all the client device other than the client-side apparatus 1 _1, in order from the speech recognition result of the client-side apparatus 1 _2, the speech recognition result of the client-side apparatus 1 ₁ and the partial strings and time If there is a match between the substring and the time, a substring that matches the pair of the substring and the time is searched. it is an example of the client-side apparatus 1 ₁ of the speech recognition result string will remove the common substring.

Speech recognition result processing unit 24 first reads a set of the speech recognition result of the client-side apparatus 1 ₁ and the time information and the ID from the speech recognition result holding unit 23 (step S241). The voice recognition result processing unit 24 then sets the initial value x to 2 (step S242). Next, the voice recognition result processing unit 24 reads the set of the voice recognition result of the client side device 1 _x , the time information, and the ID from the voice recognition result holding unit 23 (step S243). Speech recognition result processing unit 24, then, in the set of the set and the speech recognition result of the client-side apparatus 1 _x and the time information and the ID of the speech recognition result of the client-side apparatus 1 ₁ and the time information and ID, partial It is searched for whether or not there is a match between the character string and the time (step S244). In this case, since there is an error in the time, the coincidence determination is performed at an approximate time. This is within a few seconds, for example. Hereinafter, the expression “matching time” in the flow description will be treated in the same manner unless otherwise specified. Next, in step S244, if there is a partial character string whose time coincides with the time, the voice recognition result processing unit 24 determines that all the partial character strings whose time coincides with the partial character string. _{It is} removed from the character string of the voice recognition result of _{No. 1} (step S245). If there is no partial character string that matches the time in step S244, the process proceeds to step S246. Next, the voice recognition result processing unit 24 determines whether there is any client-side device that is not the target of the processing of steps S243 to S245 (step S246). If it is determined in step S246 that there is a client-side device that is not the target of the processing in steps S243 to S245, the voice recognition result processing unit 24 replaces x with x+1 (step S247). Step If it is determined that there are no remaining client device that is not subject to processing in step S243~ step S245 in S246, the last at step S245 the processed client device 1 ₁ of the speech recognition result of characters column in the ID paired as client-side apparatus 1 ₁ of processed speech recognition result string output (step S248).

Next, an example of the voice recognition result and the processed voice recognition result in this example will be described with reference to FIG. The horizontal axis of FIG. 4 is a time, three at the top of the arrow is an input and is the client-side apparatus 1 _{1-1 3} each speech recognition result of the speech recognition result processing section 24, the bottom of the arrow 1 One is a processed speech recognition result of the client-side apparatus 1 _1. The client-side apparatus 1 ₁ of the speech recognition result, the first and the partial string of the speech recognition result of speech 1 and utterance 2 is a speech the user has issued a client device 1 ₁ of the user, the client-side TV around the apparatus 1 ₁ contains a substring of the speech recognition result of the television audio 1 and the television audio 2 is a sound produced by. Moreover, the client-side apparatus 1 ₂ speech recognition result, a partial character string of the speech recognition result of the speech 3 and speech 4 is a utterance second user is a client-side apparatus 1 ₂ user uttered, substring of a speech recognition result of the client-side apparatus 1 ₂ of the television audio 1 is a audio television emitted in and around the television audio 2 are included. Further, the speech recognition result is the client-side apparatus 1 _3, and the client-side apparatus 1 ₃ third user utterance is a spoken 1 and utterance 2 of the speech recognition result emitted partial string is a user of, substring of a speech recognition result of the television audio 3 and video audio 4 is a speech television emitted around the client-side apparatus 1 ₃ are included. Here, the partial character strings of the voice recognition results of the utterances 1 and 2 which are the utterances of the first user and the voice recognition results of the utterances 1 and 2 which are the utterances of the third user It is assumed that the partial character strings are the same as each other.
To facilitate understanding of the figure, examples of character strings of uttered voice and television voice are shown together on the voice recognition result of FIG. Utterance examples are written in normal type, and TV audio examples are written in italic type. In the figure, the partial character string is written for each word, but in reality, it may be a short partial character string such as one phoneme.

First, the processing of steps S244 and S245 of FIG. 3 when x=2 will be described. The client device 1 ₁ of the substring of the speech recognition result of the television audio 1 and the television audio 2 of the partial character strings included in the speech recognition result, also includes at the same time the speech recognition result of the client-side apparatus 1 ₂ It is therefore removed from the speech recognition result of the client-side apparatus 1 _1. The substring of the utterance 1 and utterance 2 of the speech recognition result of the partial character strings included in the client-side apparatus 1 ₁ for speech recognition result is not included at the same time the speech recognition result of the client-side apparatus 1 ₂ Therefore, it not removed from the speech recognition result of the client-side apparatus 1 _1. In other words, a state in which a substring of the speech recognition result of speech 1 and utterance 2 is left as a partial character string included in the speech recognition result of the client-side apparatus 1 ₁ proceeds to the process in the case of x = 3.

Next, the processing of steps S244 and S245 of FIG. 3 when x=3 will be described. The client device 1 ₁ of the substring of the speech recognition result of speech 1 and utterance 2 of the partial character strings included in the speech recognition result, although included in the voice recognition result of the client-side apparatus 1 _3, client device because it is not included at the same time in the 1 ₃ speech recognition result, it is not removed from the speech recognition result of the client-side apparatus 1 _1. In other words, a state in which a substring of the speech recognition result of speech 1 and utterance 2 is left as a partial character string included in the speech recognition result of the client-side apparatus 1 _1.

When the processing of steps S244 and S245 of FIG. 3 when x=3 is completed, it is determined in step S246 that there is no client-side device that has not completed the processing of steps S243 to S245, and in step S248. , The speech recognition result in which the partial character strings of the speech recognition results of speech 1 and speech 2 are left is output as the processed speech recognition result.

The search processing unit 25 of the cloud-side device 2 uses the processed voice recognition result included in the set of at least one processed voice recognition result and the ID output by the voice recognition result processing unit 24 as a search query to determine a predetermined value. A search is performed in a search database or a predetermined information search site, a search result is obtained, and the obtained search result is output to the search result sending unit 26 as a set with the ID. In the above example, using the processed speech recognition result of the client device 1 ₁ speech recognition result processing unit 24 is output as a search query, executes the search at a given search database and predetermined information search site, Produced to obtain a search result corresponding to the speech recognition result, obtained results in the client device 1 ₁ of the ID and the set, and outputs the search result transmission unit 26. Since the search process is a well-known technique, detailed description will be omitted.

The search result sending unit 26 of the cloud-side device 2 transmits to the client-side device corresponding to the ID included in the set of the search result and the ID output by the search processing unit 25, which is a transmission signal including the search result. Send a signal. In the example above, it transmits the second transmission signal is a transmission signal including the search results to the client-side apparatus 1 _1. More precisely, the search result transmission unit 26, the second transmission signal is a transmission signal including the search results, to inform the client device 1 ₁ is sent to the network 3.

Search result receiving unit 14 ₁ of the client-side apparatus 1 ₁ receives the second transmission signal cloud side device 2 sends, retrieves the search results from the second transmission signal received, with respect to the screen display unit 15 ₁ Output. That is, the search result retrieval result receiving unit 14 ₁ outputs is a search result corresponding to the processed speech recognition result.

Screen display unit 15 ₁ of the client-side apparatus 1 ₁ displays a search result retrieval result receiving unit 14 ₁ is output to the client-side apparatus 1 ₁ of the screen. That is, the search result screen display section 15 ₁ is displayed is a search result corresponding to the processed speech recognition result.

By using the voice recognition system according to the first operation example of the first embodiment, the problem of Problem 1 can be solved, and the possibility that a voice recognition result different from the voice recognition result desired by the speaker can be obtained conventionally. It is possible to further reduce the possibility that a search result different from the search result desired by the speaker in the search can be obtained as compared with the conventional case.

The effect of using the voice recognition system according to the first operation example of the first embodiment will be described in more detail in the above specific case.

If the environment sound around the client-side device 1 ₁ such as a television or radio or announcement has occurred, the same television or radio or announcement with the surrounding of the client-side device 1 ₁ is also around the client-side device 1 ₂ The environmental sound such as is generated.

In this case, in the prior art, the speech recognition result of the client-side apparatus 1 _1, in addition to the speech recognition result of the first user's voice, including voice recognition result of the environmental sound, such as a television or radio or announcement Will end up. If the client-side apparatus 1 ₁ but also exist prior art speech recognition processing after applying the noise suppression processing on the sound signal obtained, there is environmental sound that could not be completely suppressed by the noise suppressing process , the speech recognition result of the client-side apparatus 1 _1, will contain the result of speech recognition has not been suppressed ambient sound.

Also present client device 1 ₁ is acquired prior art to remove an acoustic signal that the client-side apparatus 1 ₂ from the acoustic signal acquired was. However, even with the same environmental sound, because different from the transfer characteristic of the transfer characteristic and the client-side device 2 ₁ to the client-side apparatus 1 _1, the acoustic signal and the client-side apparatus 1 by the client-side apparatus 1 ₁ is acquired ₂ is included as a signal component different from the acquired acoustic signal. Therefore, at the removal of the acoustic signals by the client-side apparatus 1 ₂ from sound signals client device 1 ₁ has acquired is acquired, it is impossible to remove all environmental sound from the acoustic signal by the client-side apparatus 1 ₁ is acquired. Therefore, if there is not fully removed environment sound, the speech recognition result of the client-side apparatus 1 _1, it will contain the result of speech recognition could not remove the environmental sound. Further, when the thus removed sound signal which the client-side apparatus 1 ₂ has obtained from the audio signal by the client-side apparatus 1 ₁ is acquired, sound corresponding to the first voice user utters the client-side apparatus 1 ₁ among the components of the signal, for components corresponding to the acoustic signal of the client-side apparatus 1 ₂ will be removed, the component of the acoustic signal corresponding to the first voice user utters the client-side apparatus 1 ₁ becomes a state distorted, there is a possibility that a problem that voice recognition is not performed correctly for the first voice the user has issued the client-side apparatus 1 ₁ occurs.

Even if the transmission characteristic to the client side device 1 ₁ and the transmission characteristic to the client side device 2 ₁ are different, if the same environmental sound exists at a relatively large volume, the client side device 1 ₁ in both the speech recognition result for the acquired speech recognition result for the acoustic signals and the client-side apparatus 1 ₂ acquired acoustic signals, portions of the television or radio and announcement is a voice recognition result of the vocal such substring is the same time It is included as a string. Therefore, according to the speech recognition system according to the first operation example of the first embodiment, the speech recognition result for the sound signal by the client-side apparatus 1 ₁ has acquired, to the speech recognition result for the acoustic signal other client-side device is obtained By removing the partial character strings included at approximately the same time, it is possible to remove the speech recognition result of the environmental sound of television, radio, guide broadcast, and the like.

Meanwhile, the first voice the user has issued the client-side apparatus 1 _1, although the client-side apparatus 1 ₁ are included in the acquired acoustic signal, included in the audio signal by the client-side apparatus 1 ₂ acquires I can't. Therefore, from the speech recognition result for the sound signal by the client-side apparatus 1 ₁ is acquired, also by removing the partial character strings included in substantially the same time to the speech recognition result for the acoustic signal other client device has acquired, first The voice recognition result of the voice uttered by the user of is not removed.

As described above, according to the voice recognition system according to the first operation example of the first embodiment, the possibility that the voice recognition result of the voice uttered by the speaker, which is the voice recognition result desired by the speaker, may be omitted is reduced. , It is possible to reduce the possibility that the speech recognition result of the environmental sound such as television, radio, or guide broadcast, which is the speech recognition result different from the speech recognition result desired by the speaker, is included than before.

[[Second Operation Example of First Embodiment]]
As a second operation example, for one processing target client-side device, the same partial character string as the processing target client-side device (common partial character string) is applied to a plurality of other client-side devices that are predetermined at substantially the same time. A description will be given of an example in which a common partial character string is removed from the character string of the voice recognition result of the processing target client-side device to obtain the processed voice recognition result when is at the same time. The second operation example is different from the first operation example in the operation of the voice recognition result processing unit 24 of the cloud side device 2. Only the parts different from the first operation example will be described below.

The voice recognition result processing unit 24 of the cloud-side device 2 includes a part of the character string of the voice recognition result of at least one set of voice recognition result, time information, and ID stored in the voice recognition result holding unit 23. For each character string, a plurality of predetermined pairs (K, K is an integer of 2 or more) in which the combination of the partial character string and the time match among other combinations of the voice recognition result, the time information, and the ID. ) If there is, the processed partial speech recognition result is obtained by removing the matched partial character string, and the processed speech recognition result and the ID are output as a pair.

Next, an example of the voice recognition result and the processed voice recognition result in this example will be described with reference to FIG. The horizontal axis of FIG. 5 is a time, three at the top of the arrow is an input and is the client-side apparatus 1 _{1-1 3} each speech recognition result of the speech recognition result processing section 24, the bottom of the arrow 1 One is a processed speech recognition result of the client-side apparatus 1 _1. Here, as a more specific case, N=3 (the number of devices on the client side) and K=2 (the allowable number of devices whose partial character strings match at the same time), and the sound of TV or radio is playing. There is a first user in a place where guide broadcasting is irregularly flown, such as a train station or a department store, and a second user is in the same TV or radio as the first user or where a guide broadcast is flowing. The case where there is a third user will be described as an example.

The client-side apparatus 1 ₁ of the speech recognition result, the first and the partial string of the speech recognition result of speech 1 and utterance 2 is a speech the user has issued a client device 1 ₁ of the user, the client-side TV around the apparatus 1 ₁ contains a substring of the speech recognition result of the television audio 1 and the television audio 2 is a sound produced by. Moreover, the client-side apparatus 1 ₂ speech recognition result, a partial character string of the speech recognition result of the speech 3 and speech 4 is a utterance second user is a client-side apparatus 1 ₂ user uttered, substring of a speech recognition result of the client-side apparatus 1 ₂ of the television audio 1 is a audio television emitted in and around the television audio 2 are included. Further, the speech recognition result is the client-side apparatus 1 _3, the third user utterance and the partial string of the speech recognition result of speech 5 and the speech 2 is emitted in a client device 1 ₃ of the user, substring of client device 1 ₃ TV audio 1 is a audio television emitted around the and television audio 2 speech recognition result are included. Here, the partial character string of the speech recognition result of utterance 2 which is the utterance uttered by the first user and the partial character string of the speech recognition result of utterance 2 which is the utterance uttered by the third user are It is assumed to be the same.

Client for the substring of the speech recognition result of the speech one of device 1 ₁ of the partial character strings included in the voice recognition result, the speech recognition result of the client-side apparatus 1 _second client-side device to the speech recognition result 1 ₃ because it is not included at the same time also it is not removed from the speech recognition result of the client-side apparatus 1 _1. The substring of the speech recognition result of the television audio 1 of the partial character strings included in the client-side apparatus 1 ₁ of the speech recognition result, the client-side apparatus 1 ₃ of the speech recognition in the client-side apparatus 1 ₂ speech recognition result Since the results also include at the same time, that is, the results of speech recognition of the other two client side devices also include at the same time, the number of matches is 3 which is larger than K, and the voice of the client side device 11 is ₁ . It is removed from the recognition result. The client device 1 ₁ of the substring of the speech recognition result of the speech 2 of the partial character strings included in the speech recognition result, the speech recognition result of the client-side apparatus 1 ₂ will not be included in the same time, the client-side apparatus 1 _Since the voice recognition result of No. 3 is included at the same time, that is, the voice recognition result of the other one client-side device is also included at the same time, the number of matches is 2 and does not exceed K. not removed from the speech recognition result of the device 1 _1. The substring of the speech recognition result of the television audio 2 of the partial character strings included in the client-side apparatus 1 ₁ of the speech recognition result, the client-side apparatus 1 ₃ of the speech recognition in the client-side apparatus 1 ₂ speech recognition result since also included at the same time to the result, that is, since the speech recognition result of the other two client device included in the same time, be removed from the speech recognition result of the client-side apparatus 1 _1. Therefore, speech 1 and the client-side apparatus 1 ₁ for speech recognition result is a state in which the partial character string is left in the speech recognition result of the speech 2 is outputted as a processed speech recognition result.

It should be noted that this process may be performed for all of the other client side devices, or may be performed for some (but a plurality of) other client side devices. In this case, only the voice recognition result necessary for the processing of the voice recognition result processing section 24 may be obtained in the previous stage. That is, the operations of the voice receiving unit 21, the voice recognition unit 22, and the voice recognition result holding unit 23 for obtaining the voice recognition result unnecessary for the processing of the voice recognition result processing unit 24 may be omitted.

In the first operation example, when two users happen to utter the same content at the same time, the voice recognition result of the voice uttered by the users is removed. On the other hand, in the second operation example, unless three or more persons (K+1 or more persons) speak the same content at the same time, the voice recognition result of the voice uttered by the user is not removed. It is highly unlikely that the utterances of multiple users have the same content at the same time, compared to the fact that the environmental sounds of TV, radio, and guide broadcasting always have the same content at the same time. The above is less likely. Therefore, according to the voice recognition system in the second operation example of the first embodiment, the possibility that the voice recognition result of the voice uttered by the speaker, which is the voice recognition result desired by the speaker, may be more lost than in the first operation example. It is possible to reduce the possibility of including a voice recognition result of an environmental sound such as television, radio, or guide broadcast, which is a voice recognition result different from the voice recognition result desired by the speaker, while keeping the level low.

[[Third Operation Example of First Embodiment]]
As a third operation example, for a certain one client-side device to be processed, among other client-side devices, only the client-side device in which the same partial character string as that of the client-side device to be processed appears multiple times at the same time If the same partial character string (common partial character string) as the processing target client side device exists at the other client side device at the same time, the character string of the voice recognition result of the processing target client side device is common An example of obtaining a processed speech recognition result obtained by removing the partial character string will be described. The third operation example is different from the first operation example in the operation of the voice recognition result processing section 24 of the cloud side device 2. Only the parts different from the first operation example will be described below.

The voice recognition result processing unit 24 of the cloud-side device 2 regards at least one voice recognition result, time information, and ID set stored in the voice recognition result holding unit 23 as to another voice recognition result, time information, and ID. If there is a predetermined number (L, where L is an integer of 2 or more) in which the set of the substring matches the set of the substrings, the one obtained by removing the substring that matched The processed voice recognition result is output, and the processed voice recognition result and the ID are combined and output.

Next, an example of the voice recognition result and the processed voice recognition result in this example will be described with reference to FIG. The horizontal axis in FIG. 6 is a time, three at the top of the arrow is an input and is the client-side apparatus 1 ₁ to 1 ₃ each speech recognition result of the speech recognition result processing section 24, the bottom of the arrow 1 One is a processed speech recognition result of the client-side apparatus 1 _1. Here, as a more specific case, N=3 and L=2, and the first user is in a place where the sound of TV or radio is played or a guide broadcast such as a train station or a department store is played irregularly. There is a second user in the same TV, radio or guide broadcast as the first user and a TV, radio or guide broadcast different from the first user. The case where there is a third user will be described as an example.

The client-side apparatus 1 ₁ of the speech recognition result, the first and the partial string of the speech recognition result of speech 1 and utterance 2 is a speech the user has issued a client device 1 ₁ of the user, the client-side TV around the apparatus 1 ₁ contains a substring of the speech recognition result of the television audio 1 and the television audio 2 is a sound produced by. Moreover, the client-side apparatus 1 ₂ speech recognition result, a partial character string of the speech recognition result of the speech 3 and speech 4 is a utterance second user is a client-side apparatus 1 ₂ user uttered, substring of a speech recognition result of the client-side apparatus 1 ₂ of the television audio 1 is a audio television emitted in and around the television audio 2 are included. Further, the speech recognition result is the client-side apparatus 1 _3, the third user utterance and the partial string of the speech recognition result of speech 5 and the speech 2 is emitted in a client device 1 ₃ of the user, substring of a speech recognition result of the television audio 3 and video audio 4 is a speech television emitted around the client-side apparatus 1 ₃ are included. Here, the partial character string of the speech recognition result of utterance 2 which is the utterance uttered by the first user and the partial character string of the speech recognition result of utterance 2 which is the utterance uttered by the third user are It is assumed to be the same.

The client-side apparatus 1 ₂ speech recognition results, as a partial character string is the same substring as a speech recognition result of the client-side apparatus 1 ₁ are included at the same time, the speech recognition result of the television audio 1 substring , And a partial character string of the voice recognition result of the TV sound 2, there are two partial character strings. Client device 1 _2, since the same sub-string and the client-side apparatus 1 ₁ is a client device in a plurality of times may appear at the same time, the object of removing processing substrings. The client-side apparatus 1 ₃ of the speech recognition results, as a partial character string is the same substring as a speech recognition result of the client-side apparatus 1 ₁ are included at the same time, the partial character string of the speech recognition result of the speech 2 is there. Client device _1-3, since the same sub-string and the client-side apparatus 1 ₁ is a client device without a plurality of times may appear at the same time, it is not used for removing process of the substring. A portion for character client device 1 ₂ to be processed in the subject removing the column only in its client-side apparatus 1 ₂ speech recognition result and the client-side apparatus 1 ₁ speech recognition result, the same character string is the same time It is obtained by searching all that are included in. That is, the partial character string of the voice recognition result of the television sound 1 and the partial character string of the voice recognition result of the television sound 2 are obtained. Then, all the partial character string is searched, i.e., removing sub-string of the speech recognition result of the partial strings and TV voice second speech recognition result of the television audio 1, from the speech recognition result of the client-side apparatus 1 ₁ things, namely, obtaining speech 1 and the client-side apparatus 1 ₁ for speech recognition result is a state in which the partial character string is left in the speech recognition result of the speech 2, the resulting processed speech recognition.

It should be noted that this process may be performed for all of the other client side devices, or may be performed for some other client side devices. In this case, only the voice recognition result necessary for the processing of the voice recognition result processing section 24 may be obtained in the previous stage. That is, the operations of the voice receiving unit 21, the voice recognition unit 22, and the voice recognition result holding unit 23 for obtaining the voice recognition result unnecessary for the processing of the voice recognition result processing unit 24 may be omitted.

In the first operation example, when two users happen to utter the same content at the same time, the voice recognition result of the voice uttered by the users is removed. On the other hand, in the third operation example, unless the two users speak the same content at the same time multiple times, the voice recognition result of the voice uttered by the users is not removed. Absent. It is highly unlikely that the utterances of two users will have the same content at the same time, as compared to the environmental sound of TV, radio, or guide broadcasting, which always has the same content at the same time. It's even less likely to happen. Therefore, according to the voice recognition system in the third operation example of the first embodiment, the possibility that the voice recognition result of the voice uttered by the speaker, which is the voice recognition result desired by the speaker, may be more lost than in the first operation example. It is possible to reduce the possibility of including a voice recognition result of an environmental sound such as television, radio, or guide broadcast, which is a voice recognition result different from the voice recognition result desired by the speaker, while keeping the level low.

[[Fourth Operation Example of First Embodiment]]
As a fourth operation example, an example of using position information in addition to the time information of the first operation example will be described. Fourth operation example is different from the first operation example, the client-side apparatus ₁ 1 to 1 _N user information acquisition unit ₁₂ 1 to 12 _N, the speech recognition unit 22 of the cloud side device 2, the speech recognition result holding unit 23, This is the operation of the voice recognition result processing unit 24. Only the parts different from the first operation example will be described below.

User information acquisition section 12 ₁ of the client-side apparatus 1 _1, the client-side apparatus 1 ₁ obtains location information and time information voice input unit 11 ₁ obtains an acoustic signal, the position information and the time information as the user information and outputs to the audio transmission unit 13 _1. Position information is, for example, information indicating an absolute position such as latitude and longitude, if the client-side device is a smart phone with a built-in GPS receiver, when the microphone is a voice input unit 11 ₁ obtains a sound signal The latitude and longitude measured by the GPS receiver may be used as the position information. Further, in the case of a smartphone having a WiFi base station or an auxiliary positioning function using a beacon, the latitude and longitude measured by the auxiliary positioning unit may be used as the position information. Since the position information is used by the voice recognition result processing unit 24 in order to identify whether or not the position at which the acoustic signal acquired by each of the plurality of client-side devices is emitted is in the vicinity, Information indicating the relative positional relationship between the client side devices may be used. For example, in the case of smart TVs and STBs, the region code, postal code, beacon code received from a nearby beacon, or region-specific regions that show the same value in a mesh region of a certain latitude and longitude, such as a geohash ID. The ID may be used as information indicating the relative positional relationship of the positional information. Client device ₁ 2 to 1 _N user information acquisition unit ₁₂ 2 to 12 _N also operates in the same manner as the user information acquisition section 12 ₁ of the client-side apparatus _{1 1.}

The voice recognition unit 22 of the cloud-side device 2 performs voice recognition processing on each acoustic signal output by the voice reception unit 21, and obtains a voice recognition result that is a character string corresponding to the voice included in the acoustic signal. , A set of a voice recognition result, time information corresponding to the voice recognition result, position information corresponding to the voice recognition result, and an ID corresponding to the voice recognition result. The voice recognition process, its voice recognition result, time information corresponding to the voice recognition result, and the ID corresponding to the voice recognition result are the same as those in the first operation example. The position information to be paired with the voice recognition result is position information corresponding to the voice recognition result, that is, the user information input from the voice receiving unit 21 in combination with the acoustic signal from which the voice recognition result is obtained. Is position information included in. When there is a plurality of position information included in the user information input from the voice receiving unit 21 in combination with the acoustic signal from which the voice recognition result is obtained for one voice recognition result, One piece of position information representing the position information is paired with the voice recognition result. One piece of position information that represents a plurality of pieces of position information may be anything as long as it can roughly specify the position at which the acoustic signal corresponding to the voice recognition result is emitted, and for example, one piece of the plurality of pieces of position information. Alternatively, the position information may represent an average value of latitudes included in the plurality of position information items and an average value of longitudes included in the plurality of position information items.

The voice recognition result holding unit 23 of the cloud side device 2 stores the set of the voice recognition result output by the voice recognition unit 22, time information, position information, and ID. The contents stored in the voice recognition result holding unit 23 include a process in which the voice recognition result processing unit 24 determines whether there is a partial character string such as a word having a common time and position, and a word having a common time and position. Is used to obtain a processed voice recognition result by removing the partial character string from the voice recognition result. Therefore, the stored contents held in the voice recognition result holding unit 23 may be deleted when a certain time has elapsed after the processing of the voice recognition result processing unit 24 using the stored contents ends. This is, for example, ten and a few seconds in consideration of the time required for the internal processing of the client side device, the time and error required for data transmission to the cloud side device, the time length of each partial character string, and the like.

The voice recognition result processing unit 24 of the cloud side device 2 determines the character of the voice recognition result for at least one set of the voice recognition result with ID, time information, position information, and ID stored in the voice recognition result holding unit 23. For each pair of substring, time, and position in the sequence, other pairs of speech recognition result, time information, position information, and ID match the pair of substring, time, and position If there is, a processed speech recognition result is obtained by removing the matched partial character string, and the processed speech recognition result and the ID are output as a pair. Therefore, the processed voice recognition result for at least one certain client-side device is output. For determining whether or not the positions match, it is not determined whether or not the client-side device is in exactly the same position, but the client-side device determines whether the same sound such as TV or radio, guide broadcast, etc. Since it is determined whether or not there is a position where environmental sound may be acquired as an acoustic signal, it is determined whether or not it is in the vicinity depending on whether or not it is within a predetermined distance range. Used as a judgment. That is, if at least one client-side device has the same partial character string (common partial character string) as the client-side device in another client-side device in the vicinity at approximately the same time, A character string obtained by removing the common partial character string from the character string of the voice recognition result of the client side device is obtained as the processed voice recognition result.

It should be noted that this process may be performed on all of the other client side devices, or may be performed on at least one of the other client side devices. In this case, only the voice recognition result necessary for the processing of the voice recognition result processing section 24 may be obtained in the previous stage. That is, the operations of the voice receiving unit 21, the voice recognition unit 22, and the voice recognition result holding unit 23 for obtaining the voice recognition result unnecessary for the processing of the voice recognition result processing unit 24 may be omitted.

The processing flow of the voice recognition result determination unit 26 of the cloud side device 2 is as shown in FIG. 7. The process flow of FIG. 7 is different from the process flow of FIG. 3 in that step S241A is performed instead of step S241 of FIG. 3, step S243A is performed instead of step S243 of FIG. 3, and step S244 of FIG. The point is that step S244A is performed and step S245A is performed instead of step S245 of FIG.

Speech recognition result processing unit 24 first reads a set of the position information and the ID and the client device 1 ₁ of the speech recognition result and the time information from the speech recognition result holding unit 23 (step S241A). The voice recognition result processing unit 24 then sets the initial value x to 2 (step S242). Next, the voice recognition result processing unit 24 reads the set of the voice recognition result of the client side device 1 _x , the time information, the position information, and the ID from the voice recognition result holding unit 23 (step S243A). Speech recognition result processing unit 24, then the position information and the ID and the speech recognition result and the time information of the set and the client-side apparatus 1 _x between the position information and the ID and the client device 1 ₁ of the speech recognition result and the time information In the group of (1) and (2) are searched for whether or not there is a character string whose position matches the position of the partial character string and its approximate time (for example, several seconds) (step S244A). Next, in step S244A, if there is a partial character string that matches the time and position, the speech recognition result processing unit 24 deletes all partial character strings that match the time and position. removed from the client-side apparatus _{1 1} of the speech recognition result string (step S245A). If there is no partial character string whose time and position match in step S244A, the process proceeds to step S246. Next, the voice recognition result processing unit 24 determines whether there is any client-side device that is not the target of the processing of steps S243, S244A, and S245A (step S246). When it is determined in step S246 that there is a client-side device that is not the target of the processes of step S243, step S244A, and step S245A, the voice recognition result processing unit 24 replaces x with x+1 (step S246). S247). Step S243 In step S246, step S244A, when it is determined that there are no remaining client device that is not subject to the process of step S245A is end processed speech recognition client device _{1 1} in step S245A Been results of the string in the ID and the set output as client-side apparatus 1 ₁ of processed speech recognition result string (step S248).

Note that steps S244A11 and S244A12 described in (1) of FIG. 8 may be performed instead of step S244A of FIG. 7. By performing the step S244A11 steps S244A12 in (1) described in FIG. 8 in place of step S244A of FIG. 7, only if the set of substrings and time step S244A2 match, the client-side apparatus ₁ 2 to 1 _N since each is well be carried out of the search in the vicinity of the client-side apparatus 1 _1, when matched substring is small, it is possible to reduce the amount of computation.

Further, instead of step S244A of FIG. 7, step S244A21 and step S244A22 described in (2) of FIG. 8 may be performed. By performing the step S244A21 steps S244A22 (2) described in FIG. 8 in place of step S244A of FIG. 7, step only if the respective client-side apparatus ₁ 2 to 1 _N is close to the client device _{1 1} S244A2 Since it suffices to search for whether the set of the partial character string and the set of time coincide with each other, the calculation processing amount can be reduced when there are few client devices in the vicinity.

By using the voice recognition system according to the fourth operation example of the first embodiment, the problem of Problem 2 can be solved, and the possibility that a voice recognition result different from the voice recognition result desired by the speaker can be obtained conventionally. It is possible to further reduce the possibility that a search result different from the search result desired by the speaker in the search can be obtained as compared with the conventional case.

[[Fifth Operation Example of First Embodiment]]
Also in the fourth operation example, the same change as the operation from the first operation example to the second operation example can be made. This will be described as a fifth operation example. That is, in the fifth operation example, for one processing target client-side device, the same partial character string (as the processing target client-side device) is set to a plurality of predetermined other client-side devices that are located near each other at substantially the same time. In the case where there is a common partial character string), an example in which a common partial character string is removed from the character string of the speech recognition result of the processing target client side device is obtained as the processed speech recognition result. The fifth operation example is different from the fourth operation example in the operation of the voice recognition result processing section 24 of the cloud side device 2. Only parts different from the fourth operation example will be described below.

The voice recognition result processing unit 24 of the cloud side device 2 converts a character string of the voice recognition result for at least one set of the voice recognition result, time information, position information, and ID stored in the voice recognition result holding unit 23. For each of the included partial character strings, among a combination of the other voice recognition result, time information, position information, and ID, a plurality of sets in which the partial character string and the time set match in advance (K, If K is an integer of 2 or more), the one obtained by removing the matched partial character string is set as the processed voice recognition result, and the processed voice recognition result and the ID are output as a pair.

In the fourth operation example, when two users happen to utter the same content at the same position at the same time, the voice recognition result of the voice uttered by the users is removed. On the other hand, in the fifth operation example, unless the same content is uttered by three or more people (K+1 or more people) at the same time at the same time, the voice recognition result of the voice uttered by the user is not removed. Absent. It is highly unlikely that the utterances of multiple users will have the same content at the same time and in a nearby position, as compared to the environmental sound of TV, radio, and guide broadcasting that always has the same content at the same time. Is less likely to be three or more. Therefore, according to the voice recognition system in the fifth operation example of the first embodiment, the possibility that the voice recognition result of the voice uttered by the speaker, which is the voice recognition result desired by the speaker, may be more lost than in the second operation example. It is possible to reduce the possibility of including a voice recognition result of an environmental sound such as television, radio, or guide broadcast, which is a voice recognition result different from the voice recognition result desired by the speaker, while keeping the level low.

[[Sixth Operation Example of First Embodiment]]
The first to third operation examples that do not use position information and the fourth to fifth operation examples that use position information may be operated in combination, and an example thereof will be described as a sixth operation example. In the sixth operation example, with respect to a certain one client-side device to be processed, the client-side device determined to be in the vicinity position from the client-side device to be processed from the position information, and the one in the vicinity position to the client-side device to be processed are Although not determined, for a plurality of partial character strings in the character string of the voice recognition result, with respect to the client side device in which the same partial character string as the character string of the voice recognition result of the processing target client side device appears at the same time, This is an example of obtaining a processed voice recognition result by removing a common partial character string from the character string of the voice recognition result of the processing target client side device. The sixth operation example is different from the fourth operation example in the operation of the voice recognition result processing section 24 of the cloud side device 2. Hereinafter, an operation of the voice recognition result processing section 24 different from the fourth operation example will be described with reference to FIG. 9 which is a processing flow thereof.

Speech recognition result processing unit 24 first reads a set of the position information and the ID and the client device 1 ₁ of the speech recognition result and the time information from the speech recognition result holding unit 23 (step S241). The voice recognition result processing unit 24 then sets the initial value x to 2 (step S242). Next, the voice recognition result processing unit 24 reads the set of the voice recognition result of the client side device 1 _x , the time information, the position information, and the ID from the voice recognition result holding unit 23 (step S243). Speech recognition result processing unit 24, then the position information and the ID and the speech recognition result and the time information of the set and the client-side apparatus 1 _x between the position information and the ID and the client device 1 ₁ of the speech recognition result and the time information In the set, there is a plurality of substrings whose time coincides with that of the partial character string (step S244B1). Next, in step S244B1, the voice recognition result processing unit 24, if there are a plurality of partial character strings whose time coincides with each other, all the partial character strings whose time coincides with the partial character string on the client side. device _{1 1} removed from the string of the speech recognition result (step S245B1). In step S244B1, if there are not a plurality of substrings that match the time, that is, if there is one substring that matches the time, and if the substring matches the time. If not, the process proceeds to step S244B2. Speech recognition result processing unit 24, then the position information and the ID and the speech recognition result and the time information of the set and the client-side apparatus 1 _x between the position information and the ID and the client device 1 ₁ of the speech recognition result and the time information In the group of, there is a match between the partial character string and its time and position (step S244B2). Next, in step S244B2, if there is a partial character string that matches the time and position, the voice recognition result processing unit 24 deletes all the partial character strings that match the time and position. removed from the client-side apparatus _{1 1} of the speech recognition result string (step S245B2). If there is no partial character string whose time and position match in step S244B2, the process proceeds to step S246. Next, the voice recognition result processing unit 24 determines whether there is any client-side device that is not the processing target in any of step S243, step 244B1, step 244B2, step 245B1, and step 245B2 (step S246). If it is determined in step S246 that there is a client-side device that is not the processing target in any of step S243, step 244B1, step 244B2, step 245B1, and step 245B2, , X is replaced with x+1 (step S247). If it is determined in step S246 that there is no client-side device that is not the target of the process in any of step S243, step 244B1, step 244B2, step 245B1, or step 245B2, the process performed in step S245B1 or S245B2 performed last already client device 1 ₁ of the ID paired outputs a string of the speech recognition result as a client-side device 1 ₁ of the processed speech recognition result string (step S248).

By using the voice recognition system according to the sixth operation example of the first embodiment, a plurality of client side devices are not in the vicinity position but the same TV or radio is being played, and a plurality of client side devices are in the vicinity position. It is possible to remove the character string of the voice recognition result of the environmental sound in both cases where the same TV or radio is playing, and it is possible to obtain a voice recognition result different from the voice recognition result desired by the speaker. Therefore, it is possible to reduce the possibility of obtaining a search result different from the search result desired by the speaker in the search.

<Second Embodiment>
Next, as a second embodiment of the present invention, a mode in which a portion common to the voice recognition result of the public broadcast acoustic signal is removed from the voice recognition result of the acoustic signal including the voice of the speaker input to the client-side device explain. FIG. 10 is a block diagram showing the configuration of the voice recognition system in the second embodiment. 10 that are the same as those in FIG. 1 are given the same reference numerals. Reference numeral 100 is a voice recognition system, reference numerals 1 ₁ to 1 _N are one or more (N pieces, N is an integer of 1 or more) client side apparatuses, and reference numeral 2 is a cloud side apparatus. Reference numerals 5 _{1 to} 5 _M are public broadcasting stations of 1 station or more (M station, M is an integer of 1 or more). The client side devices 1 ₁ to 1 _N are devices used by users, and are exemplified in the description of the first embodiment, for example. The public broadcasting stations 5 _{1 to} 5 _M exist outside the voice recognition system 100. The cloud side device 2 is connected to the client side devices 1 ₁ to 1 _N via the network 3. The network 3 is for enabling the client side devices 1 ₁ to 1 _N of the voice recognition system 100 and the cloud side device 2 to send and receive information according to the connection protocol of the Internet, and is, for example, the Internet. The client side devices 1 ₁ to 1 _N and the cloud side device 2 are configured to be able to transmit and receive information according to the connection protocol of the Internet.
The cloud side device 2 is connected to the public broadcasting stations 5 _{1 to} 5 _M via the network 4. The network 4 enables the cloud-side device 2 of the voice recognition system 100 and the public broadcasting stations 5 _{1 to} 5 _M to send and receive information according to the Internet connection protocol or a dedicated protocol for video relay. , For example, closed-type private line Internet.

In the configuration of FIG. 10, the public broadcasting stations 5 _{1 to} 5 _M and the cloud side device 2 are connected via the network 4 according to the connection protocol of the Internet, and the cloud side device 2 is a public broadcasting station of the public broadcasting stations 5 _{1 to} 5 _M. Allowed to receive signals. However, the cloud side device 2 may include a receiver (not shown) so that the public broadcast signal can be received without going through the network 4. In addition, for example, since the program structure and broadcast time of public broadcasting that is broadcasted in each region such as Tokyo, Osaka, Nagoya, and Fukuyama changes, the acoustic signal also varies depending on the region. Since it is costly to install many cloud side devices 2 all over the country, receivers for public broadcasting signals are installed all over the country, and processed signals and recognition results are transmitted to the cloud side device 2 via the network 3 and the network 4. It may be configured to be sent to.

The public broadcasters 5 _{1 to} 5 _M are, for example, all or main public broadcasters in an area where the client-side device may be located, and include, for example, a residential area or a movement of a user who uses the client-side device. These include satellites, terrestrial, and major IP type broadcast/streaming/CATV/cable broadcasting that are broadcast in areas including the range. The cloud side device 2 is connected to necessary facilities such as the network 3, the network 4, the receiving facility, and the receiving device so that all desired public broadcasting stations can be received.

Since the minimum configurations included in the client side devices 1 ₁ to 1 _N are all the same, in the following, a part of the voice recognition system 100 according to the second embodiment that is configured by the client side device 1 ₁ and the cloud side device 2. This will be described with reference to FIG. 11, which is a detailed block diagram. Among the constituent elements in FIG. 11, the constituent elements denoted by the same reference numerals as those in FIG. 2 perform the same operations as those in FIG.

Client device _{1 1} includes an audio input unit 11 _1, the user information acquiring unit 12 _1, the audio output unit 13 _1, the search result receiving unit 14 _1, configured to include at least the screen display unit 15 _1.

The cloud side device 2 includes a voice receiving unit 21, a voice recognizing unit 22, a broadcast receiving unit 41, a broadcast voice recognizing unit 42, a voice recognition result holding unit 43, a voice recognition result processing unit 44, a search processing unit 25, and a search result sending unit. 26 is included at least. The voice receiving unit 21, the voice recognizing unit 22, the search processing unit 25, and the search result sending unit 26 of the cloud side device 2 are the voice receiving unit 21, the voice recognition unit 22, and the search processing unit of the cloud side device 2 of the first embodiment. 25 and the search result sending unit 26 perform the same operation.

Next, the operation of the voice recognition system of the second embodiment will be described.

[[First Operation Example of Second Embodiment]]
As a first operation example, a sentence in which each of the _first to _Nth users uses the client side devices 1 ₁ to 1 _N and the first user wants to obtain a search result for the client side device 1 ₁ the speaks, an example of operation of displaying a search result corresponding to the utterance to the client-side apparatus 1 ₁ of the screen display unit 15 _1. Here, as a more specific case, the first user is in a place where only the broadcasting of the public broadcasting station 5 ₁ is flowing in the area where the broadcasting of the _two public broadcasting stations 5 _{1 to} 52 can be received. A case will be described as an example.

Client device 1 ₁ of the speech input unit 11 ₁ obtains an acoustic signal emitted around the client-side apparatus 1 _1, and outputs the acquired audio signal to the audio transmission unit 13 _1. If the first user has uttered a sentence to be obtained search results to the client-side apparatus 1 _1, obtains and outputs a sound signal including a voice first user uttered. If the client-side apparatus 1 ₁ of environmental sounds such as a television or radio or announcement around has occurred, and outputs the acquired audio signal including the ambient sound. Therefore, if the above specific case, and audio first user has uttered, and sound public broadcasting station 5 ₁ broadcast, obtains and outputs the composed audio signal by.

User information acquisition section 12 ₁ of the client-side apparatus 1 ₁ obtains the time information voice input unit 11 ₁ of the client-side apparatus 1 ₁ acquires the audio signal, which can specify the time information and the client-side apparatus 1 ₁ identification information (hereinafter, referred to as "ID") to the audio transmission unit 13 ₁ and the user information. The time information, for example, absolute time, for example, if the client-side apparatus 1 ₁ is a smart phone with a built-in GPS receiver, the GPS receiver when the smartphone microphone is a voice input unit 11 ₁ obtains a sound signal The absolute time received by the department may be used as the time information. Further, for example, it may be time information obtained from a base station of a mobile network or a communication server, or may be time information of a local clock held by the OS.

Voice output unit 13 ₁ of the client-side apparatus 1 ₁ sends a transmission signal including the user information acoustic signal and the user information acquisition section 12 ₁ speech input unit 11 ₁ is output is output to the cloud side device 2 .. To be more precise, the voice transmitting unit 13 ₁ transmits the transmission signal including the acoustic signal output by the voice input unit 11 ₁ and the user information output by the user information acquiring unit 12 ₁ to the cloud side device 2 in order to transmit the transmission signal to the cloud side device 2. Send to 3. The transmission of the transmission signal is performed, for example, every predetermined time period such as 10 ms. The audio output unit 13 ₁ obtains a code string acoustic signal is encoded by a predetermined encoding method, it may be sent a transmission signal including a resultant code sequence and the user information. The audio output unit 13 ₁ performs such feature extraction, which is part of the processing of the speech recognition process on the acoustic signals, sends a transmission signal including a feature amount and the user information obtained by the process May be. Since there are many known technologies and well-known technologies in the technology of sending a transmission signal to another device via a network and the technology of distributing the voice recognition processing in the client side device and the cloud side device, The description is omitted.

Client device ₁ 2 to 1 _N audio input unit ₁₁ 2 to 11 _N, the user information acquiring unit ₁₂ 2 to 12 _N and the voice sending section ₁₃ 2 to 13 _N be respectively client device _{1 1} of the speech input unit 11 ₁ , the same operation as the user information acquisition unit 12 ₁ and the voice transmission unit 13 ₁ . When it is not necessary to obtain the search result corresponding to the utterance of any of the second to Nth users, the client side device of the user who does not need to obtain the search result may not be provided, and the search result may be omitted. Even if the client-side device of the user who does not need to obtain is provided, the voice input unit, the user information acquisition unit, and the voice transmission unit of the client-side device do not have to operate.

The voice receiving unit 21 of the cloud side device 2 receives the transmission signals transmitted by the voice transmitting units 13 _{1 to} 13 _N of the client side devices 1 ₁ to 1 _N , respectively, and receives the acoustic signal and the user signal from the respective received transmission signals. Take out a set of information and output it. The reception of the transmission signal is performed, for example, every predetermined time period such as 10 ms. When the voice sending units 13 _{1 to} 13 _N code the acoustic signal by a predetermined coding method to obtain a code string and send the obtained code string, the voice receiving unit 21 of the cloud side device 2 It is only necessary to obtain an acoustic signal by decoding the code string included in the received transmission signal by a decoding method corresponding to a predetermined encoding method, and output the obtained combination of the acoustic signal and the user information. In addition, the voice sending units 13 _{1 to} 13 _N perform feature amount extraction, which is a part of the voice recognition process, on the acoustic signal, and transmit a transmission signal including the feature amount and user information obtained by the process. In the case of sending, the feature amount may be extracted from the transmission signal instead of the acoustic signal, and the set of the extracted feature amount and user information may be output. If it is not necessary to obtain the search result corresponding to the utterance of any of the second to Nth users, the acoustic signal of the user who does not need to obtain the search result may not be received, and the search result may be displayed. Even if a user's acoustic signal that does not need to be obtained is received, it is not necessary to output the set of the acoustic signal and the user information. In addition, when it is not necessary to obtain the search results corresponding to the utterances of all the second to Nth users, and the set of the acoustic signal and the user information of the users other than the first user is not output, the client side device 1 The user information of ₁ may be output without including the ID.

The voice recognition unit 22 of the cloud-side device 2 performs voice recognition processing on each acoustic signal output by the voice reception unit 21, and obtains a voice recognition result that is a character string corresponding to the voice included in the acoustic signal. , A pair of a voice recognition result, time information corresponding to the voice recognition result, and an ID corresponding to the voice recognition result is output. If there is no time information or an inappropriate value, the received time information may not be used, and the server may manage the data based on the approximate time information. When not the output of the other first user, without including the ID of the client-side apparatus 1 _1, and the speech recognition result, and outputs the set by the time information corresponding to the speech recognition result Good.

The voice recognition process is performed for each predetermined group of acoustic signals. For example, the voice recognition unit 22 sequentially stores the acoustic signals output by the voice reception unit 21 in a storage unit (not illustrated) in the voice recognition unit 22, and performs utterance period detection on the stored acoustic signals to detect each utterance period. Of the acoustic signal is obtained, and voice recognition processing is performed on the group of acoustic signals for each utterance section to obtain a voice recognition result which is a character string for the group of acoustic signals for each utterance section. In addition, for example, the voice recognition unit 22 may perform voice recognition processing on a group of acoustic signals in a plurality of utterance sections to obtain a voice recognition result that is a character string for a group of acoustic signals in a plurality of utterance sections. Good.

Therefore, if the above specific case, the speech recognition unit 22, as a speech recognition result to the client-side apparatus 1 ₁ of the acoustic signal, the first user utterance voice and sound of the public broadcasting station 5 ₁ for broadcasting A character string consisting of the voice included in and the voice recognition result is obtained and output.

Note that, similarly to the first embodiment, a known voice recognition technique may be used for the voice recognition processing. When the voice receiving unit 21 outputs the feature amount instead of the acoustic signal, the voice recognizing unit 22 may perform the voice recognition process using the feature amount.

Since the voice recognition processing is performed for each predetermined group of acoustic signals, the character string of the voice recognition result corresponds to the predetermined group of acoustic signals. Therefore, for example, the voice recognition unit 22 obtains the representative time from the time information included in the plurality of user information corresponding to the predetermined set of acoustic signals subjected to the voice recognition process, and obtains the time information indicating the representative time. Pair with the voice recognition result. The representative time may be one that represents the time when the acoustic signal corresponding to the character string of the voice recognition result is emitted. For example, the start time at which the character string of the voice recognition result is emitted may be set as the representative time. Further, a plurality of representative times may be included in one voice recognition result. For example, for each partial character string such as a word included in the speech recognition result, the time at which the word or the like is emitted may be set as the representative time.

The ID paired with the voice recognition result is included in the user information input from the voice receiving unit 21 in combination with the ID corresponding to the voice recognition result, that is, the acoustic signal from which the voice recognition result is obtained. This is the ID that will be sent.

The broadcast receiving unit 41 of the cloud-side device 2 receives the public broadcast signals transmitted by the public broadcast stations 5 _{1 to} 5 _M , and outputs an acoustic signal from each received public broadcast signal and time information corresponding to the acoustic signal. The pair of and is taken out and output. At that time, identification information that can identify the public broadcasting station (hereinafter, referred to as “broadcasting station ID”) may be output as a set of the audio signal and the time information. The reception of the public broadcasting signal is performed, for example, every predetermined time period such as 10 ms. When the public broadcasting stations 5 _{1 to} 5 _N encode the acoustic signal by a predetermined encoding method to obtain a code string and send the obtained code string, the broadcast receiving unit 41 of the cloud side device 2 An acoustic signal is obtained by decoding a code string included in the received public broadcast signal by a decoding method corresponding to a predetermined encoding method, and a set of the obtained acoustic signal and time information corresponding to the acoustic signal is obtained. You can output it. The broadcast receiving unit 41 is provided with a clock (not shown) so that the absolute time can be output, and when the public broadcast signal is an analog broadcast and the time information cannot be extracted from the public broadcast signal, the broadcast receiving unit 41 can be used. The absolute time obtained from the clock provided in 41 may be output in combination with the sound signal from the public broadcast signal. Regarding the broadcast receiving unit 41, for example, since the acoustic signal group of public broadcasts to be broadcasted varies depending on each region such as Tokyo, Osaka, Nagoya, Fukuyama, etc. Alternatively, the configuration may be such that the broadcast voice recognition unit 42 is connected via a network. Further, when a signal can be directly obtained from a public broadcasting station via a network, the public broadcasting acoustic signal thus obtained may be directly used for input.

The broadcast voice recognition unit 42 of the cloud-side device 2 performs voice recognition processing on each acoustic signal output by the broadcast reception unit 41 to obtain a voice recognition result that is a character string corresponding to the voice included in the acoustic signal. Then, a set of the voice recognition result and the time information corresponding to the voice recognition result is output. At that time, the broadcasting station ID may also be output in combination with the acoustic signal and the time information. Note that the broadcast receiving unit 41 and the broadcast voice recognizing unit 42 may be configured so that their outputs are connected to the device 43 via a network in a region different from the cloud side device 2.
In addition, regarding the method of performing voice recognition processing for each predetermined group of acoustic signals and assigning time information and ID to the character string of the obtained voice recognition result, the voice recognition technology used for the voice recognition processing, etc. Since it is the same as the unit 22, detailed description will be omitted.

The voice recognition result holding unit 43 of the cloud-side device 2 includes a set of the voice recognition result output by the voice recognition unit 22, time information, and an ID, and a set of the voice recognition result output by the broadcast voice recognition unit 42 and time information. And memorize. When the broadcast voice recognition unit 42 outputs the set of the voice recognition result, the time information, and the broadcast station ID, the voice recognition result is replaced with the set of the voice recognition result and the time information output by the broadcast voice recognition unit 42. And a set of time information and broadcasting station ID are stored. The contents stored in the voice recognition result holding unit 43 include a process in which the voice recognition result processing unit 44 determines whether there is a partial character string such as a word having a common time, and a partial character string such as a word having a common time. It is used for a process of removing a speech recognition result from the speech recognition result to obtain a processed speech recognition result. Therefore, the voice recognition result holding unit 43 stores the set of the voice recognition result output by the voice recognition unit 22, the time information, and the ID, the voice recognition result output by the broadcast voice recognition unit 42, the time information, and the broadcast station ID. The set is stored for the time required for the processing of the voice recognition result processing unit 44. Further, the stored contents held in the voice recognition result holding unit 43 may be deleted when the processing of the voice recognition result processing unit 44 using the stored contents is finished.

The voice recognition result processing unit 44 of the cloud side device 2 stores in the voice recognition result holding unit 43 about the combination of the voice recognition result of the at least one client side device stored in the voice recognition result holding unit 43, the time information and the ID. If there is a match between the stored character recognition result of each public broadcast and the time information, if the combination of the partial character string and the time matches, the matched partial character string is removed and processed. As the voice recognition result, the processed voice recognition result and the ID are output as a pair. Therefore, the processed voice recognition result for at least one client-side device is output. Regarding the determination of whether or not the times match, it is determined that they are the same time in consideration of an error in absolute time between the client side device and the public broadcasting station or the cloud side device, a time error in voice recognition processing, and the like. You may. That is, if at least one client-side device has the same partial character string (common partial character string) as the client-side device in any public broadcast at approximately the same time, the client-side device The processed character recognition result is obtained by removing the common partial character string from the character string of the voice recognition result.

It should be noted that this process may be performed for all public broadcast stations in the area where the client-side device may be located, or may be performed for at least one public broadcast station. In this case, only the voice recognition result necessary for the processing of the voice recognition result processing unit 44 may be obtained in the preceding stage. That is, the operations of the broadcast receiving unit 41, the broadcast voice recognition unit 42, and the voice recognition result holding unit 43 for obtaining the voice recognition result unnecessary for the processing of the voice recognition result processing unit 44 may be omitted.

Here, in the above example of M = 2, it will be described with reference to FIGS. 12 and 13 for example at least some one client device is a client-side apparatus 1 _1. FIG. 12 is a diagram illustrating a processing flow of the voice recognition result processing unit 44 in this operation example, and FIG. 13 is a diagram illustrating an example of a voice recognition result and a processed voice recognition result in this example. In the example of FIG. 12, the speech recognition results of all the public broadcasting stations are targeted, and the speech recognition results of the client side device 1 ₁ and the set of the partial character string and the time are sequentially set from the speech recognition result of the public broadcasting station 5 _1. It is searched whether there is a match, and if there is a match in the set of the sub-character string and the time, the client side device 1 _In this example, the common partial character string is removed from the character string of the voice recognition result of _{No. 1} .

Speech recognition result processing unit 44 first reads a set of the speech recognition result of the client-side apparatus 1 ₁ and the time information and the ID from the speech recognition result holding unit 43 (step S441). The voice recognition result processing unit 44 then sets the initial value y to 1 (step S442). The voice recognition result processing unit 44 then reads the set of the voice recognition result of the public broadcasting station 5 _y and the time information from the voice recognition result holding unit 43 (step S443). Speech recognition result processing unit 44, then, in a set of client-side apparatus 1 ₁ for speech recognition result and the time information and the ID as a set and public broadcasting stations 5 _y speech recognition result and the time information of the partial strings And there is a match of the time (step S444). Next, in step S444, if there is a partial character string that matches the time, the speech recognition result processing unit 44 returns all partial character strings that match the partial character string and the time as the client side device 1. _{It is} removed from the character string of the voice recognition result of _{No. 1} (step S445). If there is no match of the partial character string with the time in step S444, the process proceeds to step S446. Next, the voice recognition result processing unit 44 determines whether there is any public broadcasting station that is not the target of the processing of steps S443 to S445 (step S446). Next, when it is determined in step S446 that there is a public broadcasting station that is not the target of the processing in steps S443 to S445, the voice recognition result processing unit 44 replaces y with y+1 (step S447). Step If it is determined that there are no remaining steps S443~ public broadcasting station that is not subject to processing in step S445 in S446, the last in step S445 the processed client device 1 ₁ of the speech recognition result of characters column in the ID paired as client-side apparatus 1 ₁ of processed speech recognition result string output (step S448).

Next, an example of the voice recognition result and the processed voice recognition result in this example will be described with reference to FIG. The horizontal axis of FIG. 13 is the time, and the three above the arrow are the voice recognitions of the client-side device 1 ₁ , the public broadcast station 5 _1, and the public broadcast station 5 ₂ which are inputs to the voice recognition result processing unit 44. the result, one below the arrow is processed speech recognition result of the client-side apparatus 1 _1. The client-side apparatus 1 ₁ of the speech recognition result, the first and the partial string of the speech recognition result of speech 1 and utterance 2 is a speech the user has issued a client device 1 ₁ of the user, the client-side TV around the apparatus 1 ₁ contains a substring of the speech recognition result of the television audio 1 and the television audio 2 is a sound produced by. Further, the speech recognition result is a public broadcasting station 5 _1, public broadcasting station 5 ₁ contains a substring of the speech recognition result of the television audio 1 and the television audio 2 is a sound included in the sound signal broadcast .. Further, the speech recognition result is a public broadcasting station 5 _2, contains a substring of the speech recognition result of the television audio 3 and video audio 4 is a sound public broadcasting station 5 ₂ is included in the acoustic signal broadcast ..

First, the processing of steps S444 and S445 of FIG. 12 when y=1 will be described. Of the partial character strings included in the voice recognition result of the client-side device 1 _1, the partial character strings of the voice recognition results of TV audio 1 and TV audio 2 are also included in the voice recognition result of the public broadcasting station 5 _{1 at} the same time. It is therefore removed from the speech recognition result of the client-side apparatus 1 _1. Of the partial character strings included in the speech recognition result of the client-side device 1 _1, the partial character strings of the speech recognition results of utterance 1 and utterance 2 are not included in the speech recognition result of the public broadcasting station 5 _{1 at} the same time. Therefore, it not removed from the speech recognition result of the client-side apparatus 1 _1. In other words, a state in which a substring of the speech recognition result of speech 1 and utterance 2 is left as a partial character string included in the speech recognition result of the client-side apparatus 1 ₁ proceeds to the process in the case of y = 2.

Next, the processing of steps S444 and S445 of FIG. 12 when y=2 will be described. The substring of the utterance 1 and utterance 2 of the speech recognition result of the partial character strings included in the client-side apparatus 1 ₁ for speech recognition result is not included at the same time the speech recognition result of the public broadcasting station 5 ₂ Therefore, it not removed from the speech recognition result of the client-side apparatus 1 _1. In other words, a state in which a substring of the speech recognition result of speech 1 and utterance 2 is left as a partial character string included in the speech recognition result of the client-side apparatus 1 _1.

When the processing of steps S444 and S445 of FIG. 12 when y=2 is completed, it is determined in step S446 that there are no public broadcasting stations left that have not completed the processing of steps S443 to S445, and in step S448. , The speech recognition result in which the partial character strings of the speech recognition results of speech 1 and speech 2 are left is output as the processed speech recognition result.

By using the voice recognition system according to the first operation example of the second embodiment, the problem of problem 1 can be solved, and the possibility that a voice recognition result different from the voice recognition result desired by the speaker can be obtained conventionally. It is possible to further reduce the possibility that a search result different from the search result desired by the speaker in the search can be obtained as compared with the conventional case.

[[Second Operation Example of Second Embodiment]]
As a second operation example, regarding a certain one of the processing target client-side devices, only the public broadcasting stations among the public broadcasting stations in which the same partial character string as the processing target client-side device appears multiple times at the same time are targeted. , If the public broadcasting station has the same partial character string (common partial character string) as the client device to be processed at the same time, remove the common partial character string from the character string of the speech recognition result of the client device to be processed. A description will be given of an example of obtaining a processed speech recognition result as a processed speech recognition result. The second operation example is different from the first operation example in the operation of the voice recognition result processing unit 44 of the cloud side device 2. Only the parts different from the first operation example will be described below.

The voice recognition result processing unit 44 of the cloud side device 2 stores in the voice recognition result holding unit 43 about the combination of the voice recognition result of the at least one client side device stored in the voice recognition result holding unit 43, the time information and the ID. The speech recognition result of the client-side device is targeted only for public broadcasting in which there are a plurality of stored pairs of the speech recognition result of public broadcasting and the time information in which the pairs of partial character strings and time match. From the character string of, the one obtained by removing the partial character string in which the combination of the partial character string and the time coincides with the speech recognition result of the public broadcasting is taken as the processed speech recognition result, and the processed speech recognition result and the ID are paired. Output. Similar to the first operation example, in determining whether the times match, an error in absolute time between the client-side device and the public broadcasting station or the cloud-side device, a time error in voice recognition processing, and the like are considered. Then, the same time may be determined. That is, in the second operation example, when at least one client-side device has the same partial character string (common partial character string) as that of the client-side device in any public broadcast at approximately the same time. Is obtained as the processed speech recognition result by removing the common partial character string for public broadcasting having a plurality of common partial character strings from the character string of the speech recognition result of the client side device.

In the first operation example, when the user accidentally utters the same content at the same time on a television or radio that does not exist as an environmental sound around the user, the voice recognition result of the voice uttered by the user is It will be removed. On the other hand, in the second operation example, unless the user speaks the same content multiple times at the same time on the TV or radio that does not exist as an environmental sound around the user, the voice uttered by the user It does not remove the speech recognition result. It is extremely unlikely that the user accidentally speaks the same content at the same time on a television or radio that does not exist as an environmental sound around the user, and it is even less likely that it will occur multiple times. Therefore, according to the voice recognition system of the second operation example of the second embodiment, the possibility that the voice recognition result of the voice uttered by the speaker, which is the voice recognition result desired by the speaker, may be more lost than in the first operation example. It is possible to reduce the possibility of including a voice recognition result of an environmental sound such as television, radio, or guide broadcast, which is a voice recognition result different from the voice recognition result desired by the speaker, while keeping the level low.

[[Third Operation Example of Second Embodiment]]
As a third operation example, an example will be described in which position information is used in addition to the time information of the first operation example. The third operation example differs from the first operation example, the client-side apparatus ₁ 1 to 1 _N user information acquisition unit ₁₂ 1 to 12 _N, the speech recognition unit 22 of the cloud side device 2, the broadcast receiving unit 41, broadcast audio These are operations of the recognition unit 42, the voice recognition result holding unit 43, and the voice recognition result processing unit 44. Only the parts different from the first operation example will be described below.

User information acquisition section 12 ₁ of the client-side apparatus 1 ₁ of the third operation example, the client-side apparatus 1 ₁ obtains location information and time information voice input unit 11 ₁ obtains an acoustic signal, the position and the time information and outputs to the audio transmission unit 13 ₁ of the information as the user information. Position information is, for example, information indicating an absolute position such as latitude and longitude, if the client-side device is a smart phone with a built-in GPS receiver, GPS when the microphone is a voice input unit 11 ₁ obtains a sound signal The latitude and longitude measured by the receiver may be used as the position information. In the case of a smartphone having a WiFi base station or an auxiliary positioning function using a beacon, the latitude and longitude measured by the auxiliary positioning unit may be used as the position information. The position information may be information indicating a relative positional relationship between a plurality of client-side devices. For example, in the case of smart TVs and STBs, the region code, postal code, beacon code received from a nearby beacon, or region-specific regions that show the same value in a mesh region of a certain latitude and longitude, such as a geohash ID. The ID may be used as information indicating the relative positional relationship of the positional information. Client device ₁ 2 to 1 _N user information acquisition unit ₁₂ 2 to 12 _N also operates in the same manner as the user information acquisition section 12 ₁ of the client-side apparatus _{1 1.}

The voice recognition unit 22 of the cloud-side device 2 of the third operation example performs voice recognition processing on each acoustic signal output by the voice reception unit 21, and outputs a voice that is a character string corresponding to the voice included in the acoustic signal. A recognition result is obtained, and a set including a voice recognition result, time information corresponding to the voice recognition result, position information corresponding to the voice recognition result, and an ID corresponding to the voice recognition result is output. The voice recognition process, its voice recognition result, time information corresponding to the voice recognition result, and the ID corresponding to the voice recognition result are the same as those in the first operation example. The position information paired with the voice recognition result is position information corresponding to the voice recognition result, that is, the user information input from the voice receiving unit 21 in combination with the acoustic signal from which the voice recognition result is obtained. Is position information included in. When there is a plurality of position information included in the user information input from the voice receiving unit 21 in combination with the acoustic signal from which the voice recognition result is obtained for one voice recognition result, a plurality of position information is obtained. One piece of position information representing the position information is paired with the voice recognition result. One piece of position information representing a plurality of pieces of position information may be anything as long as the position at which the acoustic signal corresponding to the voice recognition result is generated can be substantially specified. For example, one piece of the plurality of pieces of position information. Alternatively, it may be position information indicating an average value of latitude included in a plurality of position information and an average value of longitude included in a plurality of position information.

Among the operations performed by the broadcast receiving unit 41 of the cloud-side device 2 of the third operation example, the operation different from the operation performed by the broadcast receiving unit 41 of the first operation example is that the broadcast station ID is always output, that is, the acoustic signal. And outputting the set of time information and broadcasting station ID. The other operations are the same as those in the first operation example.

Among the operations performed by the broadcast voice recognition unit 42 of the cloud-side device 2 of the third operation example, the operation different from the operation performed by the broadcast voice recognition unit 42 of the first operation example is that the broadcast station ID is always input/output, that is, The point is that the set of the acoustic signal, the time information, and the broadcast station ID is input, and the set of the character string of the voice recognition result, the time information, and the broadcast station ID is output. The other operations are the same as those in the first operation example.

The voice recognition result holding unit 43 of the cloud-side device 2 of the third operation example includes the set of the voice recognition result output by the voice recognition unit 22, time information, position information, and ID, and the voice output by the broadcast voice recognition unit 42. The recognition result, the time information, and the set of the broadcasting station ID are stored. The contents stored in the voice recognition result holding unit 43 include a process in which the voice recognition result processing unit 44 determines whether or not a client-side device exists in a reception area of public broadcasting, and a partial character string such as a word having a common time. It is used for a process for determining whether or not there is a partial character string such as a word having a common time and a process for removing a partial character string from a voice recognition result to obtain a processed voice recognition result. Therefore, the voice recognition result holding unit 43 includes a set of the voice recognition result output by the voice recognition unit 22, time information, position information, and ID, the voice recognition result output by the broadcast voice recognition unit 42, the time information, and the broadcast station. The combination with the ID is stored for the time required for the processing of the voice recognition result processing unit 44. Further, the stored contents held in the voice recognition result holding unit 43 may be deleted when the processing of the voice recognition result processing unit 44 using the stored contents is finished.

The voice recognition result processing unit 44 of the cloud-side device 2 of the third operation example relates to the combination of the voice recognition result of the at least one client-side device, the time information, the position information, and the ID stored in the voice recognition result holding unit 43. , In the set of the voice recognition result of each public broadcast, the time information, and the broadcast station ID stored in the voice recognition result holding unit 43, there is a client-side device in the receiving area of the public broadcast, and the partial character string and the time When there is a match with the pair of and, the one obtained by removing the matched partial character string is the processed voice recognition result, and the processed voice recognition result and the ID are output as a pair. Therefore, the processed voice recognition result for at least one client-side device is output.

Whether or not the client-side device is in the public broadcast reception target area may be determined by matching publicly known information that can specify the absolute position. For example, in a storage unit (not shown) in the voice recognition result processing unit 44, information such as a country, a prefecture, a municipality, etc. to which a broadcasting station ID of a public broadcast is received and a map with latitude and longitude are stored in advance. Every other day, the country, prefecture, municipality, etc. in which the client side device is located are obtained from the latitude and longitude specified by the position information of the client side device, and the country, prefecture, municipality, etc. is the target country, prefecture, municipality for receiving public broadcasting. It may be determined depending on whether or not Alternatively, for example, in a storage unit (not shown) in the voice recognition result processing unit 44, information on the latitude/longitude range of the reception target area of the broadcasting station ID of the public broadcast is stored in advance and specified by the position information of the client side device. The determination may be made based on whether the latitude/longitude of the position at which the acoustic signal corresponding to the voice recognition result is emitted is within the latitude/longitude of the reception area.

Regarding the determination of whether or not the times match, it is determined that they are the same time in consideration of an error in absolute time between the client side device and the public broadcasting station or the cloud side device, a time error in voice recognition processing, and the like. You may.

That is, the speech recognition result processing unit 44 of the cloud-side device 2 of the third operation example applies to at least one client-side device at a substantially same time to the public broadcast in the reception target area of the client-side device. When there is the same partial character string as the client side device (common partial character string), the one obtained by removing the common partial character string from the character string of the voice recognition result of the client side device is obtained as the processed voice recognition result. ..

Note that the process of removing the common partial character string does not necessarily have to be performed by the client-side device for all public broadcasting stations that are the reception target area, but may be performed for at least one public broadcasting. In this case, only the voice recognition result necessary for the processing of the voice recognition result processing unit 44 may be obtained in the preceding stage. That is, the operations of the broadcast receiving unit 41, the broadcast voice recognition unit 42, and the voice recognition result holding unit 43 for obtaining the voice recognition result unnecessary for the processing of the voice recognition result processing unit 44 may be omitted.

Here it will be described with reference to the processing flow in FIG. 14 for example at least some one client device is a client-side apparatus 1 _1. Example of FIG. 14, as the target speech recognition results of all public broadcasting station, in order from the public broadcasting station 5 _1, it is determined whether the received target area of the public broadcasting stations have client-side apparatus 1 _1, the public if the received target area of the broadcast station is a client-side device 1 _1, the speech recognition result of the public broadcasting station, those set of the speech recognition result of the client-side apparatus 1 ₁ and the partial strings and time matches Whether or not there is a match between the pairs of the partial character string and the time, a partial character string matching the pair of the partial character string and the time is recognized by the client-side device ₁₁ by voice recognition. In this example, the common character string is removed from the resulting character string.

Speech recognition result processing unit 44 first reads a set of the position information and the ID and the client device 1 ₁ of the speech recognition result and the time information from the speech recognition result holding unit 43 (step S441A). The voice recognition result processing unit 44 then sets the initial value y to 1 (step S442). The voice recognition result processing unit 44 then reads the set of the voice recognition result of the public broadcasting station 5 _y , the time information, and the broadcast station ID from the voice recognition result holding unit 43 (step S443A). Speech recognition result processing unit 44, then, a set of client-side apparatus 1 ₁ speech recognition result and the time information and the position information and the speech recognition result sets and public broadcasting stations 5 _y of the ID and the time information and the broadcast station ID And, the result of voice recognition of the client-side device 11 and the position information included in the set of time information and position information are included in the receiving area of the public broadcasting station 5 _y , and the partial character string and the time match. It is searched whether there is any (step S444A). Speech recognition result processing unit 44, then, when conditions are satisfied in step S444A removes all partial strings substring and its time matches the client-side apparatus 1 ₁ of the speech recognition result string (Step S445A). If the condition of step S444A is not satisfied, the process proceeds to step S446. Next, the voice recognition result processing unit 44 determines whether there is any public broadcasting station that is not the target of the processing of steps S443, S444A, and S445A (step S446). When it is determined in step S446 that there remains a public broadcasting station that is not the target of the processing in step S443, step S444A, and step S445A, the voice recognition result processing unit 44 replaces y with y+1 (step S447). Step S443 In step S446, step S444A, when it is determined that there are no remaining public broadcasting station that is not subject to the process of step S445A is end processed speech recognition client device _{1 1} in step S445A Been results of the string in the ID and the set output as client-side apparatus 1 ₁ of processed speech recognition result string (step S448).

By using the voice recognition system according to the third operation example of the second embodiment, it is less likely that the voice recognition result of the voice uttered by the speaker, which is the voice recognition result desired by the speaker, will be lost as compared with the first operation example. It is possible to solve the problem of Problem 1 while suppressing the problem, reduce the possibility that a speech recognition result different from the speech recognition result desired by the speaker is obtained, and the search result desired by the speaker in the search is reduced. It is possible to reduce the possibility that different search results will be obtained as compared with the conventional case.

<Third Embodiment>
Next, as a third embodiment of the present invention, the result of voice recognition of an acoustic signal including the voice of the speaker input to the client side device is the same as the result of voice recognition of the acoustic signal reproduced by the client side device. The form of removing a part will be described. The configuration of the voice recognition system in the third embodiment is similar to the configuration of the voice recognition system in the first embodiment, and a block diagram showing the configuration of the voice recognition system is FIG. Reference numeral 100 is a voice recognition system, reference numerals 1 ₁ to 1 _N are one or more (N pieces, N is an integer of 1 or more) client side apparatuses, and reference numeral 2 is a cloud side apparatus. In the third embodiment, each of the client side devices 1 ₁ to 1 _N has a function of reproducing the content stored in the client side device and/or a function of reproducing the content while the client side device downloads via the network 3. Is. As for the “stored contents”, a medium may be attached. The content includes an audio signal including at least voices in Japanese and foreign languages such as serifs. For example, a movie recorded on a client side device, a package program downloaded and purchased, and a VOD played back while being downloaded by the client side device. Is an audiovisual signal such as.

Since the configurations included in the client side devices 1 ₁ to 1 _N at least are the same, in the following, in the speech recognition system 100 according to the third embodiment, a part configured by the client side device 1 ₁ and the cloud side device 2. This will be described with reference to FIG. 15 which is a detailed block diagram. Among the constituent elements in FIG. 15, constituent elements designated by the same reference numerals as those in FIG. 11 perform the same operations as those in FIG.

Client device _{1 1} includes an audio input unit 11 _1, the user information acquiring unit 12 _1, the audio output unit 13 _1, the search result receiving unit 14 _1, the screen display unit 15 _1, the content information obtaining unit 16 _1, the contents information sending part 17 ₁ is included at least. The voice input unit 11 ₁ , the user information acquisition unit 12 ₁ , the voice transmission unit 13 ₁ , the search result reception unit 14 ₁ , and the screen display unit 15 ₁ of the client side device 1 ₁ are the clients of the first operation example of the second embodiment. The voice input unit 11 ₁ , the user information acquisition unit 12 ₁ , the voice transmission unit 13 ₁ , the search result reception unit 14 ₁ , and the screen display unit 15 _{1 of the} side device 1 ₁ respectively perform the same operation.

The cloud side device 2 includes a voice receiving unit 21, a voice recognizing unit 22, a content voice recognizing result accumulating unit 60, a content information receiving unit 61, a content voice recognizing result acquiring unit 62, a voice recognizing result holding unit 63, a voice recognizing result processing unit. 64, a search processing unit 25, and a search result sending unit 26. The voice receiving unit 21, the voice recognizing unit 22, the search processing unit 25, and the search result sending unit 26 of the cloud side device 2 are the voice receiving unit 21 and the voice recognition unit of the cloud side device 2 of the first operation example of the second exemplary embodiment. 22, the search processing unit 25, and the search result sending unit 26 perform the same operations.

Below, a part different from the first operation example of the second embodiment will be described.

Client device 1 ₁ of the content information acquisition unit 16 _1, the content that the client-side apparatus 1 ₁ is currently reproduced, identification information capable of identifying the content (hereinafter, referred to as "content ID". In the same movies However, the dialogue differs depending on the language selection such as Japanese and foreign languages.In the following explanation, in the case of content that supports audio in multiple languages such as Japanese and foreign languages, each has a different content ID. treated as possible to, and omitted), the relative time that represents the position currently being played during the content (a so-called playback position), to obtain the outputs to the content information sender 17 _1. The relative time that represents the part currently playing in the content is, for example, the number of seconds required to play that part when playing at the standard speed from the beginning start point of the content, or the content For example, a time stamp that is given in advance.

The content information sender 17 _first client-side apparatus 1 _1, identifiable identification information client device 1 ₁ (hereinafter, referred to as "ID") and the content ID and the relative time that the content information acquisition unit 16 ₁ is output If, by the time information which the user information acquisition section 12 ₁ has output, and to set, to the ID and the content ID and the third transmission signal cloud side device 2 is a transmission signal including a set of the relative time and the time information To send. Note that the identification information may be specified by using an existing external cloud service that can acquire the content ID and the relative time (playback position) from the information database of the optical medium or fragmentary audio data, for example.

In the content voice recognition result storage unit 60 of the cloud side device 2, the content ID of the content such as a movie and the character string of the voice recognition result obtained by voice recognition of the acoustic signal of the content are stored in advance in the content voice recognition result storage unit 60. The time and are stored in association with each other. The character string of the voice recognition result and the relative time are stored by combining the partial character string and the relative time for each partial character string included in the character string of the voice recognition result.

The content information reception unit 61 of the cloud side device 2 receives the third transmission signal content information sender 17 _first client device 1 ₁ is transmitted, ID and the content ID and the relative included in the third transmission signal A set of time and time information is obtained and output to the content voice recognition result acquisition unit 62.

The content voice recognition result acquisition unit 62 of the cloud-side device 2 searches the content voice recognition result storage unit 60 using the content ID output by the content information reception unit 61 and the relative time, and outputs the voice of the content corresponding to the content ID. A set of the partial character string and the relative time for each partial character string included in the character string of the recognition result is obtained, and the relative time is replaced with the time information output by the corresponding content information receiving unit 61 to obtain the content. A pair of the partial character string and time information for each partial character string included in the character string of the voice recognition result is generated, and the corresponding partial character string for each partial character string included in the generated character string of the voice recognition result and A set of time information and an ID are output as a set to the voice recognition result holding unit 63.

The voice recognition result holding unit 63 of the cloud-side device 2 stores a set of the voice recognition result output by the voice recognition unit 22, time information, and an ID, and a character string of the voice recognition result output by the content voice recognition result acquisition unit 62. For each of the included partial character strings, a set of the partial character string, time information, and an ID is stored. The contents stored in the voice recognition result holding unit 63 include a process in which the voice recognition result processing unit 64 determines whether there is a partial character string such as a word having a common time, and a partial character string such as a word having a common time. It is used for a process of removing a speech recognition result from the speech recognition result to obtain a processed speech recognition result. Therefore, the stored contents held in the voice recognition result holding unit 63 may be deleted when the processing of the voice recognition result processing unit 64 using the stored contents is completed.

The voice recognition result processing unit 64 of the cloud side device 2 stores in the voice recognition result holding unit 43 about the set of the voice recognition result of the at least one client side device stored in the voice recognition result holding unit 63, the time information and the ID. A combination of a partial character string and time in a combination of the partial character string, time information set and ID for each partial character string included in the stored character string of the voice recognition result If there is, the processed speech recognition result is obtained by removing the matched partial character strings, and the processed speech recognition result and the ID are output as a pair. It should be noted that in determining whether the times match, it may be determined that they are the same time in consideration of a time difference in the voice recognition processing. Processing Flow in at least some one client device is a client-side apparatus 1 ₁ is as shown in FIG 16.

As described above, according to the third embodiment, for example, when playing a movie or VOD, the content ID and the number of seconds of the playing position are also sent to the cloud-side device 2 together with the acoustic signal acquired by the client-side device. As a result, the cloud-side device 6 searches the DB in which the voice recognition result of the content is accumulated according to the content ID and the number of seconds of the reproduction position, and obtains the voice recognition result of the voice sound of the content (character string of announcement or dialogue). , The user of the client side device removes the voice recognition result of the voice sound of the obtained content (character strings of announcements and dialogue) as noise from the character string of the voice recognition result of the acoustic signal acquired by the client side device. It is possible to reduce the probability of erroneous recognition of voice recognition for the utterance uttered by.

That is, the problem of Problem 3 can be solved by using the voice recognition system according to the third embodiment.

<Fourth Embodiment>
Next, as the fourth embodiment of the present invention, a mode in which the input of the search instruction is specified will be described. Here, a mode in which the input of the search instruction is specified in the second embodiment of FIG. 11 will be described with reference to FIG. FIG. 17 is a detailed block diagram of a portion of the speech recognition system 100 according to the fourth embodiment corresponding to the second embodiment, which includes the client-side device ₁₁ and the cloud-side device 2. The configuration shown in FIG. 17 is different from the configuration shown in FIG. 11 in that the client-side device 1 ₁ is configured to include at least the search instruction input unit 18 ₁ . The components other than the search instruction input unit 18 _{1 in} FIG. 17 are the same as those in FIG. The differences from the description of the second embodiment will be described below.

[[Operation Example of Fourth Embodiment]]
As an operation example of the fourth embodiment, the first user utters a sentence to the client-side device 1 ₁ for which a search result is desired, and the search result corresponding to the utterance is displayed on the screen display unit of the client-side device 1 _1. an example of an operation of displaying the 15 ₁ will be described.

The search instruction input unit 18 ₁ of the client-side device 1 ₁ receives an input of a search start instruction when the first user speaks a sentence for which a search result is desired, and inputs the received search start instruction by voice. The data is output to the unit 11 ₁ , the user information acquisition unit 12 _1, and the voice transmission unit 13 ₁ . The search start instruction can be said to be an instruction to start both voice recognition and search. For example, if the client-side apparatus 1 ₁ is a smart phone, a voice search start button displayed on a screen, detecting means for detecting that the voice search start button is touched, the client device 1 ₁ This is the search instruction input unit 18 ₁ .

Client device 1 ₁ of the speech input unit 11 ₁ in accordance with the instruction of the search instruction input unit 18 ₁ is output search start obtains the acoustic signal, and outputs the acquired audio signal to the audio output unit 13 _1. For example, the speech input unit 11 _1, the acquisition of the acoustic signal at the time when the search start instruction starts acquisition of acoustic signals at the time of the input, the time search start instruction is predetermined from the time input has elapsed To finish. Point addition, for example, the speech input unit 11 _1, which comprises a speech detecting means (not shown), an instruction to start searching starts acquisition of acoustic signals at the time of the input is determined that the speech detecting means has disappeared speech This completes the acquisition of the acoustic signal.

User information acquisition section 12 ₁ of the client-side apparatus 1 ₁ search instruction in accordance with an instruction input portion 18 ₁ is the search start outputting, to obtain time information voice input unit 11 ₁ of the client-side apparatus 1 ₁ acquires the audio signal Te, the time information and the client-side apparatus 1 ₁ can specify identification information (hereinafter, referred to as "ID") to the audio output unit 13 ₁ and the user information. For example, the user information acquisition unit 12 ₁ acquires time information while the audio input unit 11 ₁ acquires and outputs the acoustic signal, and the acquired time information and ID are used as user information in the audio transmission unit 13 _1. Output to.

User information sound output unit 13 ₁ of the client-side apparatus 1 ₁ according to an instruction of the search instruction input unit 18 searches _{started 1} is output, the acoustic signal and the user information acquisition section 12 ₁ speech input unit 11 ₁ is output is output A transmission signal including and is sent to the cloud side device 2.

The subsequent operation of the speech recognition system 100 of the operation example of the fourth embodiment is the same as that of the first operation example of the second embodiment.

With this configuration, in response to the retrieval instruction input unit 18 ₁ of the client-side apparatus 1 ₁ accepts the input of a search start instruction, corresponding to the sentence to be obtained search results first user has uttered it is possible to display the search results to the client-side apparatus 1 ₁ of the screen display unit 15 _1.

It should be noted that the operation of the voice recognition system 100 in which the input of the search instruction is specified is the same as the above in the operation examples other than the first operation example of the second embodiment, the first embodiment, and the third embodiment, and thus detailed description will be given. Although not described, when the search instruction input unit of the client-side device receives the input of the search start instruction, the search result corresponding to the sentence that the user wants to obtain the search result is displayed on the client-side device. It can be displayed on the screen display unit.

<Modification of Fourth Embodiment>
Next, as a modified example of the fourth embodiment of the present invention, a mode in which the acoustic signal before the input time point of the search instruction is used will be described with reference to FIG. FIG. 18 is a detailed block diagram of a portion of the speech recognition system 100 according to the modified example of the fourth embodiment shown in FIG. 17, which includes the client-side device ₁₁ and the cloud-side device 2. The configuration shown in FIG. 18 is different from the configuration shown in FIG. 17 in that the client side device 1 ₁ is configured to include at least the voice holding unit 19 ₁ . The components other than the voice holding unit _{1 in} FIG. 18 are the same as those in FIG. The difference from the fourth embodiment will be described below.

[[Operation Example of Modification of Fourth Embodiment]]
As an example of the operation of the modification of the fourth embodiment, an example of the same case as the operation of the fourth embodiment, i.e., speaks a sentence to be obtained search results first user to the client-side apparatus 1 ₁ , an example of operation of displaying a search result corresponding to the utterance to the screen display unit 15 ₁ of the client-side apparatus 1 _1.

Speech input unit 11 ₁ of the client-side apparatus 1 ₁ always acquires an acoustic signal. When a search start instruction is input from the search instruction input unit 18 ₁ , the voice input unit 11 ₁ follows the search start instruction input from the search instruction input unit 18 ₁ and outputs the acquired acoustic signal as a voice output unit. 13 to output to _1. For example, when the search start instruction is input from the search instruction input unit 18 ₁ , the voice input unit 11 ₁ starts in advance from the time when the search start instruction is input and the time when the search start instruction is input. up to the point where an agreement time elapses, and outputs a sound signal to the sound output unit 13 _1. Further, the voice input unit 11 ₁ outputs all the acquired acoustic signals to the voice holding unit 19 ₁ .

The user information acquisition unit 12 ₁ of the client-side device 1 ₁ always acquires the time information of the time when the audio input unit 11 ₁ acquires the acoustic signal. When a search start instruction is input from the search instruction input unit 18 ₁ , the user information acquisition unit 12 ₁ follows the search start instruction input from the search instruction input unit 18 ₁ and outputs the voice of the client-side device 1 ₁ . and time information of an acoustic signal input unit 11 ₁ outputs the voice output unit 13 _1, the speech the time information and the client-side apparatus 1 ₁ can specify identification information (hereinafter, referred to as "ID") and a user information and outputs to the transmission unit 13 _1. In addition, the user information acquisition unit 12 ₁ outputs all the acquired time information to the voice holding unit 19 ₁ .

Client device 1 ₁ of the speech holding unit 19 ₁ stores in the storage unit (not shown) by the time information input from the sound signal and the user information acquisition unit 12 ₁ that is input from the speech input unit 11 ₁ in the set, The set of the acoustic signal and the time information which has passed a predetermined time since the latest one is deleted from the storage unit. That is, the voice holding unit 19 ₁ holds the acoustic signal input from the voice input unit 11 ₁ and the time information corresponding to the acoustic signal for a predetermined time from the latest one. The predetermined time is a preset time, and is, for example, about ten seconds to several minutes. Further, when the search start instruction is input from the search instruction input unit 18 ₁ , the voice holding unit 19 ₁ sends the set of the acoustic signal and the time information stored in the storage unit to the voice sending unit 13 ₁ . Output. That is, when a search start instruction is input from the search instruction input unit 18 ₁ , the voice holding unit 19 ₁ outputs an acoustic signal for a predetermined time from the latest one and its time information to the voice sending unit 13 ₁ . To do.

Voice output unit 13 ₁ of the client-side apparatus 1 ₁ search in accordance with an instruction of search start input from the instruction input unit 18 ₁ is input from the audio signal and the user information acquisition unit 12 ₁ that is input from the speech input unit 11 ₁ The transmission signal including the user information, the acoustic signal input from the voice holding unit 19 ₁ and the time information thereof is sent to the cloud side device 2. That is, the voice output unit 13 _1, the acoustic signal up to the point of time when the search instruction starts when an instruction to start searching has been input a predetermined from the time input has elapsed and its time information, initiating searches instructions than when it is inputted sends a past audio signal in a predetermined time duration and its time information, and the ID of the client-side apparatus 1 _1, a transmission signal including the cloud side device 2.

The operations of the voice receiving unit 21, the voice recognizing unit 22, the broadcast receiving unit 41, and the broadcast voice recognizing unit 42 of the cloud-side device 2 are respectively the voice receiving unit 21, the voice recognizing unit 22, and the broadcast receiving unit 41 of the second embodiment. The operation is the same as that of the broadcast voice recognition unit 42.

The voice recognition result processing unit 44 of the cloud side device 2 firstly determines the voice recognition result holding unit, the time information and the ID of the voice recognition result of at least one client side device stored in the voice recognition result holding unit 43. The speech of the client-side device is targeted only for public broadcasting in which there are a plurality of pairs of partial character strings and times that match the speech recognition result of public broadcasting and time information stored in 43. From the character string of the recognition result, the character string of the speech recognition result of the client side device after the removal is obtained by removing the partial character string whose pair of partial character string and time matches the speech recognition result of the public broadcast. The speech recognition result processing unit 44 further processes the character string of the speech recognition result of the client-side device after the removal, which is obtained by removing the partial character string in the past from the time when the search start instruction is input, as the processed speech recognition. As a result, the processed voice recognition result and the ID are output as a pair.

Next, an example of the voice recognition result and the processed voice recognition result in this example will be described with reference to FIG. The horizontal axis of FIG. 19 is a time search instruction time the T ₀ of the time of the _input, the search instruction is time to T _A at which time a predetermined from the time T ₀ that is input has _elapsed, the search instruction Let T _{B be} the time point a predetermined time before the input time point T ₀ . Three above the thick arrow in the upper is an input client device 1 ₁ and each of the speech recognition result of the public broadcasting station 5 ₁ and public broadcasting station 5 ₂ of the speech recognition result processing section 44, the lower one below the thick arrow in the are processed speech recognition result of the client-side apparatus 1 _1.

The client-side apparatus 1 ₁ of the speech recognition results, search instruction as the result time of the speech recognition until the time T _A the time determined in advance from the time T ₀ that is input has elapsed, the client-side apparatus 1 ₁ of the user there first user and a sub-string of the speech recognition result of the speech 2 is a speech uttered substring of a speech recognition result of the television audio 2 is a audio television emitted around the client-side apparatus 1 ₁ And, are included. Moreover, the client-side apparatus 1 ₁ of the speech recognition results, as the predetermined time speech recognition result of time from past time T _B until time T ₀ the search instruction is input at time T ₀ the search instruction is input, first user and a sub-string of the speech recognition result of the speech 1 is a speech uttered, TV voice is the voice of television emitted around the client-side apparatus 1 ₁ is a client-side apparatus 1 ₁ of the user And a partial character string of the voice recognition result of No. 1 are included.

A public broadcasting station 5 ₁ for speech recognition result, the search instruction as the result time of the speech recognition until the time T _A the time determined in advance from the time T ₀ that is input has elapsed, public broadcasting station 5 ₁ is broadcast sound It includes a partial character string of the voice recognition result of TV voice 2 which is the voice included in the signal. Further, the speech recognition result of the public broadcasting station 5 _1, as a predetermined time speech recognition result of time from past time T _B until time T ₀ the search instruction is input at time T ₀ the search instruction is input, public broadcasting station 5 ₁ contains a substring of the speech recognition result of the television audio 1 is a sound included in the sound signal broadcast.

A public broadcasting station 5 ₂ of the speech recognition results, search instruction as the result time of the speech recognition until the time T _A the time determined in advance from the time T ₀ that is input has elapsed, public broadcasting station 5 ₂ is broadcast sound It includes a partial character string of the voice recognition result of the TV voice 4, which is the voice included in the signal. Also, the public broadcasting station 5 ₂ of the speech recognition results, as the predetermined time speech recognition result of time from past time T _B until time T ₀ the search instruction is input at time T ₀ the search instruction is input, public broadcasting station 5 ₂ contains a substring of the speech recognition result of the television audio 3 is a sound included in the sound signal broadcast.

In the character string of the voice recognition result of the client side device 1 ₁ and the character string of the voice recognition result of the public broadcasting station 5 ₁ , a partial character string and its time match between time T _B and time T _A. , There are two partial character strings of the voice recognition result of TV voice 1 and the voice recognition result of TV voice 2. Thus, public broadcasting station 5 ₁ for a plurality of substrings, for partial strings and their time are the same, the removed target. Then, the voice recognition result processing unit 44 has the same partial character string at the same time from the character string of the voice recognition result of the client side device 1 ₁ to the character string of the voice recognition result of the public broadcasting station 5 ₁ . All the partial character strings of the voice recognition result of the TV voice 1 and the partial character strings of the voice recognition result of the TV voice 2 are removed. The client-side apparatus 1 of the _first speech recognition result string and public broadcasting station 5 ₂ of the speech recognition result string, while from the time T _B at time T _A, the partial character string and its time matches parts There is no character string. Thus, public broadcasting stations 5 _2, for a plurality of substrings, for partial strings and their time do not match, not a removed object. Client device 1 ₁ of a result of removing the processing up to this point for the character string of the speech recognition result is an illustration between the upper thick arrow and the lower thick arrow in FIG. 19.

Then, the speech recognition result processing unit 44, the client-side apparatus 1 ₁ of the speech recognition result string, the partial character is a sequence of speech first speech recognition result sub-string between times T ₀ from the time T _B Get rid of. As a result, those only partial string of the speech recognition result of the speech 2 is left is outputted as processed speech recognition result of the client-side apparatus 1 _1.

The subsequent operation of the voice recognition system 100 of the operation example of the modified example of the fourth embodiment is the same as that of the operation example of the fourth embodiment.

Similarly to the modification of the fourth embodiment, also all embodiments operation example of the first to third embodiments, the like comprises a speech holding unit 19 _1, than search start instruction of the past acoustic The signal may be used to operate the speech recognition system 100.

By adopting a configuration in which an acoustic signal earlier than the search start instruction is used as in the modification of the fourth embodiment, in particular, the third operation example of the first embodiment and the second operation example of the second embodiment are performed. In the configuration for performing the speech recognition result removal processing for other client-side devices or public broadcasting stations that share a plurality of partial character strings as in the operation example, a configuration that does not use an acoustic signal past the search start instruction is used. The response speed can be increased as compared with the case of performing.

<Embodiment of voice recognition device>
Although the above-described voice recognition system has a configuration in which the client side devices 1 ₁ to 1 _N and the cloud side device 2 are connected by the network 3, the cloud side device 2 may be configured by a plurality of server devices or the like. Good. The voice recognition system does not have to be a cloud type system, but may be a stand-alone type voice recognition device. That is, it may be a voice recognition device provided with the configuration of the cloud-side device 2 in each of the client-side devices 1 ₁ to 1 _N.

Further, in the above description, an example in which the voice recognition result is applied to information retrieval has been described, but the voice recognition result may be used in any way. That may be a speech recognition device including an only essential part of the portion constituted by the client-side apparatus 1 ₁ and the cloud side device 2 shown in FIGS. 2 and 11. These voice recognition devices will be described with reference to FIG.

[[First example of voice recognition device]]
FIG. 20A is a block diagram showing a first example of the voice recognition device. The voice recognition device 700 of the first example is configured to include at least a voice recognition unit 710 and a voice recognition result 720.

The voice recognition unit 710 of the voice recognition device 700 corresponds to the voice recognition unit 22 of FIG. For example, the voice recognition unit 710 is a first sound that is a sound signal that is collected by the first sound collecting unit such as the microphone of the smartphone of the first speaker who is the voice recognition target and includes the first speaker sound. 2nd to Nth sound pickup means different from the first sound pickup means such as the microphone of the smartphone of each of the signals and the second to Nth users (N is an integer of 2 or more) different from the first speaker. The first acoustic recognition result, which is the speech recognition result for each acoustic signal, of the second acoustic signal to the Nth acoustic signal, which are the acoustic signals collected respectively, and the Nth speech. Get recognition results. Here, the 1st sound signal-the Nth sound signal are sound signals containing the same time, for example. For example, the first acoustic signal is an acoustic signal including a voice uttered by the first speaker as a voice recognition target, and the second acoustic signal to the Nth acoustic signal have the same start and end as the first acoustic signal. Alternatively, it is an acoustic signal that is an absolute time in the vicinity.

The voice recognition result processing unit 720 of the voice recognition device 700 corresponds to the voice recognition result holding unit 23 and the voice recognition result processing unit 24 of FIG. For example, the voice recognition result processing unit 720 includes the partial voice recognition result included in at least one voice recognition result of the second voice recognition result to the Nth voice recognition result, and the partial voice recognition result included in the first voice recognition result. And are the partial speech recognition results having the same content of the partial speech recognition results and corresponding to the acoustic signals at substantially the same time, the partial speech recognition result is deleted from the first speech recognition result. The result is obtained as the voice recognition result of the first speaker. In addition to the fact that the partial voice recognition results are the same and the times are substantially the same, the voice recognition result processing unit 720 places the second to Nth sound pickup means in the vicinity of the first sound pickup means. In some cases, the partial voice recognition result may be deleted from the first voice recognition result.

[[Second example of voice recognition device]]
FIG. 20B is a block diagram showing a second example of the voice recognition device. The voice recognition device 701 of the second example is configured to include at least a voice recognition unit 711 and a voice recognition result 721.

The voice recognition unit 711 of the voice recognition device 701 corresponds to the voice recognition unit 22 and the broadcast voice recognition unit 42 of FIG. 11. For example, the voice recognition unit 711 is a first sound that is a sound signal that is collected by the first sound collecting unit such as the microphone of the smartphone of the first speaker who is the voice recognition target and includes the first speaker sound. Signal, and the first broadcast sound signal to the Mth broadcast sound signal (M is an integer of 1 or more), which are one or more broadcast sound signals, are speech-recognized, and sound for each sound signal is recognized. The first voice recognition result and the first broadcast voice recognition result to the Mth broadcast voice recognition result, which are the recognition results, are obtained. Here, the first sound signal and the first broadcast sound signal to the Mth broadcast sound signal are sound signals including the same time, for example. For example, the first acoustic signal is an acoustic signal including a voice uttered by the first speaker as a voice recognition target, and the first broadcast acoustic signal to the Mth broadcast acoustic signal have first and second end acoustic signals, respectively. Is an acoustic signal that is the same or near absolute time as.

The voice recognition result processing unit 721 of the voice recognition device 701 corresponds to the voice recognition result holding unit 43 and the voice recognition result processing unit 44 of FIG. 11. For example, the voice recognition result processing unit 721 may include a partial voice recognition result included in at least one voice recognition result of the first broadcast voice recognition result to the Mth broadcast voice recognition result, and a partial voice included in the first voice recognition result. When the recognition result is the same as the partial voice recognition result and is the partial voice recognition result corresponding to the acoustic signals at substantially the same time, the partial voice recognition result is deleted from the first voice recognition result. What is obtained as the speech recognition result of the first speaker. Note that the voice recognition result processing unit 721 targets only the voice recognition results of the second to Mth broadcasts in which the first sound collecting unit is in the reception target area, the contents of the partial voice recognition results are the same, and the times are substantially the same. When it is, the partial speech recognition result may be deleted from the first speech recognition result.

According to these voice recognitions, even if the user speaks in an environment where the environmental sound such as television, radio, or guide broadcasting exists at a relatively large volume, the speech recognition of the environmental sound can be performed with high accuracy. Since the result can be removed and the possibility that an unnecessary voice recognition result is included, the voice recognition rate for the voice of the speaker can be improved.

In the above description, the speech recognition result is described as a character string, but when the speech recognition result is represented by a string of symbols representing phonemes, a string of phoneme symbols is used instead of the character string. May be. That is, the character string or partial character string of the speech recognition result in the above description is an example of the speech recognition result such as the phoneme symbol string or the partial phoneme symbol string of the speech recognition result, or a part of the content thereof.

All or part of the voice recognition system in the above-described embodiment may be realized by a computer. In that case, the program for realizing this function may be recorded in a computer-readable recording medium, and the program recorded in this recording medium may be read by a computer system and executed. The “computer system” mentioned here includes an OS and hardware such as peripheral devices. The "computer-readable recording medium" refers to a portable medium such as a flexible disk, a magneto-optical disk, a ROM, a CD-ROM, or a storage device such as a hard disk built in a computer system. Further, the "computer-readable recording medium" means to hold a program dynamically for a short time like a communication line when transmitting the program through a network such as the Internet or a communication line such as a telephone line. In this case, a volatile memory inside a computer system that serves as a server or a client in that case may hold a program for a certain period of time. Further, the program may be for realizing a part of the above-mentioned functions, or may be a program for realizing the above-mentioned functions in combination with a program already recorded in a computer system, It may be realized by using hardware such as PLD (Programmable Logic Device) or FPGA (Field Programmable Gate Array).

Although the embodiments of the present invention have been described with reference to the drawings, the above embodiments are merely examples of the present invention, and it is obvious that the present invention is not limited to the above embodiments. is there. Therefore, additions, omissions, replacements, and other changes of the constituent elements may be made without departing from the technical idea and scope of the present invention.

The present invention recognizes an audio signal including the input voice of a speaker by voice recognition, even when a voice with a relatively large volume exists in the background of the voice that the speaker wants to recognize. Obtaining a result, recognizing another input audio signal as a voice, obtaining a recognition result, and removing the common one of these recognition results from the voice recognition result of the input acoustic signal By reducing the possibility that the recognition result is included, the speech recognition rate for the voice of the speaker is improved. Therefore, even if there is a comparatively loud sound in the background of the voice that the speaker wants to recognize, it can be used in various applications where it is essential to obtain the voice recognition result of only the voice of the speaker. Can also be applied.

For example, in a living room of a general household, according to the present invention, it is not necessary to separate the position of the sound source from the speaker sound source such as a TV or AV amplifier, the remote control device with a voice recognition microphone is not required, and the height inside the device housing is increased. You will be able to recognize the voice only with the sensitivity microphone. Therefore, convenience is improved by reducing the cost of the terminal system, which is severe in device cost, reducing the weight of the remote controller, and reducing the power consumption of the remote controller.

In addition, the present invention provides a sound at a TV or radio with little silence or unvoiced sound during broadcasting, an Olympic venue, a station, an airport, a lecture hall, a train, a public viewing venue, etc. in which a place information broadcast is repeated in multiple languages. It is useful for utilizing recognition.

Further, according to the present invention, even in an automobile, utterance of a voice recognition command and related information by voice recognition can be performed at any time without worrying about the voice sound (announcement, dialogue) of a stand-alone car TV, traffic information, or car radio. Search can be done. As a result, it is expected that the cloud-based voice agent service for automobiles will be more convenient.

Also, in the voice command recognition of the automatic telephone answering system in the call center of the company, it is possible to suppress the influence of daily voice noise such as TV or radio voice that is often in the background at the user's home, so that the accuracy is improved, and eventually the accuracy is improved. As a side effect, cost reduction by reducing operator intervention operation can be expected.

1 ₁ , 1 ₂ , 1, _3, 1 _N ... Client side device, 2... Cloud side device, 3... Network, 100... Voice recognition system, 11 ₁ ... Voice input unit, 12 ₁ ... user information acquiring unit, ₁₃ 1 ... audio sending unit, ₁₄ 1 ... retrieval result receiving unit, ₁₅ 1 ... image display unit, 21 ... audio receiving unit, 22 ... sound recognition unit, 23 ... speech recognition result holding unit, 24 ... speech recognition result processing unit, 25 ... retrieval processing unit, 26 ... retrieval result transmission _unit, 5 _{1, 5} M ... public broadcasting Bureau, 41 ... broadcast receiving unit, 42 ... broadcast audio recognition unit, 43 ... speech recognition result holding portion, 44 ... speech recognition result processing unit, ₁₆ 1 ... content information acquisition unit, 17 ₁ ...Content information sending unit, 60...Content voice recognition result storage unit, 61...Content information receiving unit, 62...Content voice recognition result acquisition unit, 63...Voice recognition result holding unit, 64... Voice recognition result processing unit, 18 ₁ ... Search instruction input unit, 19 ₁ ... Voice holding unit, 700... Voice recognition device, 710... Voice recognition unit, 720... Voice Recognition result processing unit, 701... Voice recognition device, 711... Voice recognition unit, 721... Voice recognition result processing unit

Claims (8)

The first sound signal, which is a sound signal that includes the sound of the first speaker by the first sound collecting unit, and one or more broadcasts acquired from the public broadcasting station connected according to the Internet connection protocol. First sound recognition which is a sound recognition result for each sound signal by sound-recognizing each sound signal of the first broadcast sound signal to the M-th broadcast sound signal (M is an integer of 1 or more) which are sound signals. Result and first broadcast voice recognition result to voice recognition means for obtaining Mth broadcast voice recognition result,
The partial voice recognition result included in the at least one voice recognition result of the first broadcast voice recognition result to the Mth broadcast voice recognition result and the partial voice recognition result included in the first voice recognition result are the partial voice recognitions. When the content of the result is the same and the partial speech recognition result corresponding to the acoustic signals at substantially the same time, the partial speech recognition result deleted from the first speech recognition result is the first utterance. Voice recognition result processing means to be obtained as a voice recognition result of a person,
Equipped with
The voice recognition result processing means,
The partial voice recognition result included in the at least one voice recognition result of the first broadcast voice recognition result to the Mth broadcast voice recognition result and the partial voice recognition result included in the first voice recognition result are the partial voice recognitions. Only the first broadcast speech recognition result to the Mth broadcast speech recognition result, which have the same result and have a plurality of partial voice recognition results corresponding to acoustic signals at substantially the same time, are recognized. In the result and the partial voice recognition result included in the first voice recognition result, the partial voice recognition result has the same content, and all the partial voice recognition results corresponding to the acoustic signals at substantially the same time are obtained and obtained. A voice recognition device that obtains a result obtained by deleting the obtained partial voice recognition result from the first voice recognition result as a voice recognition result of the first speaker. The first sound recognition result, which is the sound recognition result of the first sound signal, is obtained by recognizing the sound of the first sound signal, which is the sound signal picked up by the first sound collecting means, including the sound of the first speaker. And voice recognition of the first broadcast sound signal to the Mth broadcast sound signal (M is an integer of 1 or more), which is one or more broadcast sound signals received by a receiver installed in a public broadcast signal reception target area. And a voice recognition means for obtaining the first broadcast sound signal to the Mth broadcast sound recognition result, which is the sound recognition result of the first broadcast sound signal to the Mth broadcast sound signal, through a network,
Among the first broadcast voice recognition result to the Mth broadcast voice recognition result, the partial voice recognition result included in at least one voice recognition result in the area where the first sound collecting unit receives the broadcast, and the first voice recognition result. When the partial voice recognition result included in the voice recognition result is the same as the partial voice recognition result and is the partial voice recognition result corresponding to the acoustic signals at substantially the same time, the partial voice recognition result is A voice recognition result processing means for obtaining what is deleted from the first voice recognition result as a voice recognition result of the first speaker;
Voice recognition device. Voice recognition of the first acoustic signal by voice-recognizing the first acoustic signal, which is the acoustic signal collected by the first sound collecting means included in the client device used by the user, including the voice of the first speaker. The first voice recognition result, which is the result, and the first broadcast, which is an audio signal of one or more broadcasts received by the cloud device installed in the receiving area of the public broadcast signal and connected to the client device via the network. Acoustic signal-M-th broadcast acoustic signal (M is an integer of 1 or more) is voice-recognized, and first broadcast acoustic signal-First broadcast voice recognition result which is the voice recognition result of the M-th broadcast acoustic signal-M-th broadcast voice recognition A voice recognition means for obtaining the result,
Among the first broadcast voice recognition result to the Mth broadcast voice recognition result, the partial voice recognition result included in at least one voice recognition result in the area where the first sound collecting unit receives the broadcast, and the first voice recognition result. When the partial voice recognition result included in the voice recognition result is the same as the partial voice recognition result and is the partial voice recognition result corresponding to the acoustic signals at substantially the same time, the partial voice recognition result is A voice recognition result processing means for obtaining what is deleted from the first voice recognition result as a voice recognition result of the first speaker;
Voice recognition device. The voice recognition result processing means,
The partial voice recognition result included in the at least one voice recognition result of the first broadcast voice recognition result to the Mth broadcast voice recognition result and the partial voice recognition result included in the first voice recognition result are the partial voice recognitions. Only the first broadcast speech recognition result to the Mth broadcast speech recognition result, which have the same content of the results and have a plurality of partial voice recognition results corresponding to the acoustic signals at substantially the same time, are recognized. In the result and the partial voice recognition result included in the first voice recognition result, the partial voice recognition result has the same content, and all the partial voice recognition results corresponding to the acoustic signals at substantially the same time are obtained and obtained. The speech recognition device according to claim 2 or 3, wherein a result obtained by deleting the obtained partial speech recognition result from the first speech recognition result is obtained as a speech recognition result of the first speaker. A voice recognition device is obtained from a public broadcasting station connected according to an Internet connection protocol, and a first acoustic signal that is an acoustic signal collected by the first sound collecting unit including the voice of the first speaker. The first broadcast sound signal to the Mth broadcast sound signal (M is an integer of 1 or more), which are the sound signals of one or more broadcasts, are sound-recognized, and the sound recognition result for each sound signal is obtained. A certain first voice recognition result and a first broadcast voice recognition result to a voice recognition step of obtaining a Mth broadcast voice recognition result;
A voice recognition device includes a partial voice recognition result included in at least one voice recognition result of the first broadcast voice recognition result to the Mth broadcast voice recognition result, and a partial voice recognition result included in the first voice recognition result. However, if the partial voice recognition results have the same content and the partial voice recognition results corresponding to the acoustic signals at substantially the same time, the partial voice recognition result is deleted from the first voice recognition result. A voice recognition result processing step obtained as a voice recognition result of the first speaker;
Have
In the voice recognition result processing step,
The partial voice recognition result included in the at least one voice recognition result of the first broadcast voice recognition result to the Mth broadcast voice recognition result and the partial voice recognition result included in the first voice recognition result are the partial voice recognitions. Only the first broadcast speech recognition result to the Mth broadcast speech recognition result, which have the same result and have a plurality of partial voice recognition results corresponding to acoustic signals at substantially the same time, are recognized. In the result and the partial voice recognition result included in the first voice recognition result, the partial voice recognition result has the same content, and all the partial voice recognition results corresponding to the acoustic signals at substantially the same time are obtained and obtained. A speech recognition method for obtaining a result obtained by deleting the obtained partial speech recognition result from the first speech recognition result as a speech recognition result of the first speaker. The voice recognition device voice-recognizes the first acoustic signal, which is the acoustic signal collected by the first sound collecting unit including the voice of the first speaker, and is the voice recognition result of the first acoustic signal. The first voice recognition result and the first broadcast sound signal to the Mth broadcast sound signal (M is 1 or more) that is the sound signal of one or more broadcasts received by the receiver installed in the area where the public broadcast signal is received. A voice recognition step for recognizing the first broadcast sound signal through the network to obtain the first broadcast sound recognition result, which is the sound recognition result of the Mth broadcast sound signal, through the network. ,
The voice recognition device includes a partial voice recognition result included in at least one voice recognition result of the first broadcast voice recognition result to the Mth broadcast voice recognition result in which the first sound collecting unit is in the broadcast receiving area. And the partial voice recognition result included in the first voice recognition result has the same content of the partial voice recognition result and is a partial voice recognition result corresponding to acoustic signals at substantially the same time, A voice recognition result processing step of obtaining a result obtained by deleting the partial voice recognition result from the first voice recognition result as a voice recognition result of the first speaker;
A speech recognition method having. The voice recognition device voice-recognizes a first acoustic signal, which is an acoustic signal collected by the first sound collecting means included in the client device used by the user, including the voice of the first speaker, and first A first voice recognition result, which is a voice recognition result of the acoustic signal, and one or more broadcast acoustic signals received by a cloud device installed in a receiving area of the public broadcast signal and connected to the client device via a network. First broadcast sound signal-Mth broadcast sound signal (M is an integer of 1 or more) is speech-recognized and first broadcast sound signal-First broadcast sound recognition result which is the sound recognition result of the Mth broadcast sound signal- A voice recognition step of obtaining a M-th broadcast voice recognition result,
The voice recognition device includes a partial voice recognition result included in at least one voice recognition result of the first broadcast voice recognition result to the Mth broadcast voice recognition result in which the first sound collecting unit is in the broadcast receiving area. And the partial voice recognition result included in the first voice recognition result has the same content of the partial voice recognition result and is a partial voice recognition result corresponding to acoustic signals at substantially the same time, A voice recognition result processing step of obtaining a result obtained by deleting the partial voice recognition result from the first voice recognition result as a voice recognition result of the first speaker;
A speech recognition method having. A voice recognition program for causing a computer to operate as the voice recognition device according to claim 1.

Images