JP7159773B2 - VOICE OPERATING DEVICE, VOICE OPERATING METHOD, AND VOICE OPERATING SYSTEM - Google Patents

Description

The present invention relates to a voice operation device, a voice operation method , and a voice operation system.

2. Description of the Related Art In recent years, smart speakers that recognize a user's uttered voice and perform device operation, information search, etc. according to the recognition result have become popular (see Patent Documents 1 and 2, for example). A smart speaker acquires voice data uttered by a user through a microphone and recognizes the voice data. When the smart speaker recognizes an utterance of a word called a hot word (also called a wake word) for activating the smart speaker, it transitions from the standby state to the activated state in which device operation, information search, etc. are possible. After transitioning to the activation state, the smart speaker operates, for example, home appliances such as an air conditioner, or performs information search using the recognition result as a keyword, according to the recognition result of the voice data uttered by the user.

JP 2017-76117 A Japanese Patent Publication No. 2016-505888

A smart speaker is assigned one fixed word as a hot word. Therefore, when a hot word is reproduced in a television commercial message (Commercial Message) or the like of a smart speaker, the smart speaker may react to the sound output from the television and activate the smart speaker.

In addition, a malicious third party outside the home remotely operates a playback device capable of audio output (for example, a speaker-equipped phone) installed in the same user's home where the smart speaker is installed. It is also assumed that audio is output from the device. In this case, the third party can activate the smart speaker by playing back the voice of the hot word from the playback device, and then operate the home appliance or the like by voice. In this way, when the hotword is fixed, there is a problem that a third party may operate the device in the house or use the service by spoofing.

Such challenges are not limited to smart speakers, but equally apply to other voice-operated devices such as set-top boxes that are activated by voice recognition of hotwords and subsequently accept voice commands.

The present invention has been made in view of such circumstances, and provides a voice operation device, a voice operation method, a computer program, and a voice capable of preventing unauthorized voice operations by a third party other than the user of the voice operation device. The object is to provide an operating system.

(1) To achieve the above object, a voice operation device according to an embodiment of the present invention includes a display control unit that displays hot words on a screen, a voice acquisition unit that acquires voice data uttered by a user, an utterance determination unit that determines whether or not the hot word has been uttered based on the voice data; and a voice operation unit that permits voice operation by the user when it is determined that the hot word has been uttered. Prepare.

(11) A voice operation method according to another embodiment of the present invention comprises the steps of: displaying a hot word on a screen; obtaining voice data uttered by a user; determining whether or not the hotword has been spoken; and permitting the voice operation by the user if it is determined that the hotword has been spoken.

(12) A computer program according to another embodiment of the present invention is a computer program comprising: a display control unit for displaying hot words on a screen; a voice acquisition unit for acquiring voice data uttered by a user; and a voice operation unit that permits voice operation by the user when it is determined that the hot word has been uttered.

(13) A voice operation system according to another embodiment of the present invention comprises a display device, a display control section for displaying a hot word on the screen of the display device, and a voice acquisition section for acquiring voice data uttered by a user. an utterance determination unit that determines whether or not the hot word has been uttered based on the voice data; and a voice operation unit that permits voice operation by the user when it is determined that the hot word has been uttered. Prepare.

The present invention can also be implemented as a semiconductor integrated circuit that implements part or all of the voice operation device.

According to the present invention, unauthorized voice operation by a third party other than the user of the voice operation device can be prevented.

1 is a diagram showing the configuration of a voice operation system according to an embodiment of the present invention; FIG. It is a flow chart which shows an example of a processing procedure of STB (Set Top Box: Set Top Box) concerning an embodiment of the invention. It is a figure which shows an example of operation|movement of the voice operation system which concerns on embodiment of this invention.

[Overview of Embodiments of the Present Invention]
First, an overview of the embodiments of the present invention will be listed and explained.
(1) A voice operation device according to an embodiment of the present invention includes a display control unit that displays hot words on a screen, a voice acquisition unit that acquires voice data uttered by a user, and based on the voice data, An utterance determination unit that determines whether or not a hot word has been uttered, and a voice operation unit that permits a voice operation by the user when it is determined that the hot word has been uttered.

According to this configuration, the hotword is displayed on the screen, and the voice operation by the user is permitted when the hotword displayed on the screen is spoken. For this reason, a third party who cannot see the screen cannot know the hotword and cannot utter the hotword, thereby rejecting the voice operation by the third party. Therefore, unauthorized voice operation by a third party other than the user of the voice operation device can be prevented.

(2) Preferably, the screen is co-located with the voice operation device.

According to this configuration, the hotword is displayed on the screen in the same place as the voice operation device, and the user's voice operation is permitted when the hotword displayed on the screen is spoken. Therefore, for example, a third party who is not in the home of the user where the voice operation device is installed cannot see the screen and cannot know the hotword. Therefore, the third party cannot utter the hotword, thereby rejecting the voice operation by the third party. Therefore, unauthorized voice operation by a third party other than the user of the voice operation device can be prevented.

(3) More preferably, the display control unit displays the hot word on the screen for a predetermined period of time, and the speech determination unit displays the hot word based on the voice data uttered during the predetermined period of time. Determine whether a hotword has been spoken.

According to this configuration, voice operation can be permitted only when the hotword is spoken while the hotword is displayed on the screen. Therefore, the voice operation is not permitted based on other hotwords displayed on the screen in the past. This makes it possible to further prevent unauthorized voice operations by a third party.

(4) Further, the display control unit may change the hotword according to a predetermined change condition.

According to this configuration, even if the hotword is disclosed to a third party, the hotword is changed according to the predetermined change conditions, thereby preventing unauthorized voice operations by the third party. In addition, it is possible to reduce the possibility that the voice operation device will be activated in response to the voice of a TV commercial that reads a fixed hot word.

(5) Further, the display control unit may periodically change the hotword.

According to this configuration, since the hotword is changed periodically, it is possible to further prevent unauthorized voice operations by a third party.

(6) Further, the display control section may change the hot word based on the determination result of the speech determination section.

According to this configuration, the hotword can be changed according to the determination result of whether or not the hotword has been uttered. You can change the hotword to e.g.

(7) Further, the display control unit may change the hotword based on the number of times it is determined that the hotword is not uttered.

According to this configuration, for example, when it is determined that the hot word has not been uttered a predetermined number of times in succession, the hot word can be changed. Therefore, if a third party attempts to operate the voice operation device by, for example, outputting voice from the playback device by remote control and fails, the hot word can be changed. As a result, it is possible to prevent the voice operating device from being illegally operated by a third party.

(8) Further, the display control unit may change the hotword when the voice operation is finished.

According to this configuration, the hotword can be changed each time the voice operation by the user is completed. This makes it difficult for the hot word to be exposed to a third party, and prevents the voice operation device from being illegally operated by a third party.

(9) Further, the display control section may select a word from a plurality of words pre-stored in a storage section, and display the selected word on the screen as the hot word.

According to this configuration, a word stored in advance in the storage unit can be used as a hot word, so that a voice recognition model capable of recognizing the word can be created before shipment of the voice operation device. Therefore, it is not necessary to learn the speech recognition model before the utterance judging section performs judgment processing by speech recognition.

(10) Further, the display control unit may display the word determined by the user on the screen as the hot word.

According to this configuration, since a word determined by the user can be used as a hotword, the hotword can be freely determined, thereby making it difficult for the hotword to be exposed to a third party.

(11) A voice operation method according to another embodiment of the present invention includes the steps of displaying a hot word on a screen, acquiring voice data uttered by a user, and generating the hot word based on the voice data. determining whether or not the hotword has been spoken; and permitting the voice operation by the user if it is determined that the hotword has been spoken.

This configuration includes steps corresponding to the characteristic processing units included in the voice operation device described above. Therefore, it is possible to obtain the same actions and effects as those of the voice operation device described above.

(12) A computer program according to another embodiment of the present invention provides a computer program comprising: a display control unit for displaying a hot word on a screen; a voice acquisition unit for acquiring voice data uttered by a user; and a voice operation unit that permits voice operation by the user when it is determined that the hot word has been uttered.

According to this configuration, the computer can function as the voice operation device described above. Therefore, it is possible to obtain the same actions and effects as those of the voice operation device described above.

(13) A voice operation system according to another embodiment of the present invention includes a display device, a display control unit that displays hot words on the screen of the display device, and a voice acquisition unit that acquires voice data uttered by a user. an utterance determination unit that determines whether or not the hot word has been uttered based on the voice data; and a voice operation unit that permits voice operation by the user when it is determined that the hot word has been uttered. Prepare.

This voice operation system includes the voice operation device described above as a configuration. Therefore, it is possible to obtain the same actions and effects as those of the voice operation device described above.

[Details of the embodiment of the present invention]
BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. It should be noted that each of the embodiments described below is a preferred specific example of the present invention. Numerical values, shapes, materials, components, arrangement positions and connection forms of components, steps, order of steps, and the like shown in the following embodiments are examples and are not intended to limit the present invention. The invention is defined by the claims. Therefore, among the constituent elements in the following embodiments, the constituent elements not described in the independent claims representing the top concept of the present invention are not necessarily required to achieve the object of the present invention, but are more It is described as constituting a preferred form.

Moreover, the same code|symbol is attached|subjected to the same component. Since their functions and names are also the same, description thereof will be omitted as appropriate.

<Overall configuration of voice operation system>
FIG. 1 is a diagram showing the configuration of a voice operation system according to an embodiment of the present invention.
Referring to FIG. 1, voice operation system 1 includes STB 10 and display device 20 .

The STB 10 functions as a voice operation device, acquires voice data of voice uttered by the user 40, and operates the STB 10 or household appliances such as the air conditioner 30 connected to the STB 10 based on the acquired voice data. In addition to the voice data of the voice uttered by the user 40 himself/herself, the voice data of the voice uttered by the user 40 may include the voice data of the voice uttered by the user 40 by operating a device capable of uttering voice. Also includes audio data. For example, when the user 40 with speech impairment operates a speech synthesizer, the speech data of the synthesized speech uttered by the device is also included in the speech data of the speech uttered by the user 40 . That is, the voice data of the voice uttered by the user 40 indicates the voice data of the voice based on the intention of the user 40 to utter.

Note that the household equipment is not limited to the air conditioner 30, and may be other equipment as long as it is connected to the STB 10 by wire or wirelessly. For example, the household appliance may be a lighting fixture that turns on or off or adjusts the amount of light according to instructions from the STB 10 .

Also, the voice operation device is not limited to the STB 10, and may be any other device as long as it can be voice operated based on voice data uttered by the user 40. FIG. For example, the voice control device may be a smart speaker that retrieves information or controls home appliances based on voice data.

The display device 20 is connected to the STB 10 by wire or wirelessly. The display device 20 is, for example, a display device connected to the STB 10 via an HDMI (registered trademark) (High-Definition Multimedia Interface) cable. The display device 20 displays video data or image data output from the STB 10 on the screen. Note that the display device 20 may be incorporated in the STB 10 or a voice operation device such as a smart speaker. That is, the voice operation device may have a display screen. Conversely, the display device 20 may have built-in functions such as the STB 10 or a smart speaker.

The STB 10 displays a hot word used for activating functions related to voice operation of the STB 10 itself (a voice operation unit 13 and a playback processing unit 14, which will be described later) and used for permitting voice operation by the user 40, on the display device. 20 is displayed.

The STB 10 includes a voice acquisition section 11 , a voice recognition section 12 , a voice operation section 13 , a reproduction processing section 14 , a video output section 15 , a hot word display control section 16 and a storage section 17 .

The voice acquisition unit 11 acquires voice data uttered by the user 40 . Specifically, the voice acquisition unit 11 includes a microphone, converts voice input to the microphone into voice data by A/D (Analog to Digital) conversion, and acquires voice data after conversion. do.

The voice recognition unit 12 functions as an utterance determination unit, and determines whether or not the user 40 has uttered a hot word based on the voice data acquired by the voice acquisition unit 11 . That is, the speech recognition unit 12 performs speech recognition processing on the speech data, and determines whether or not the speech data includes the uttered speech of the hot word. The voice recognition unit 12 transmits a determination result signal indicating the determination result to the voice operation unit 13 and hot word display control unit 16 .

A known technique can be used for the speech recognition processing. For example, speech recognition processing can be performed using a Hidden Markov Model, a neural network machine-learned by deep learning, or the like.

Note that the speech recognition unit 12 can also recognize words other than hot words. For example, the speech recognition unit 12 can also recognize words for operating the air conditioner 30 (for example, "30° C.", "power on", etc.) from the speech data. The voice recognition section 12 transmits the voice recognition result to the voice operation section 13 .

Voice operation unit 13 receives the determination result signal and the voice recognition result from voice recognition unit 12 . When the determination result signal indicates that a hot word has been uttered, the voice operation unit 13 permits the voice operation by the user 40 and executes the voice operation based on the received voice recognition result.

For example, when the voice recognition result indicates "air conditioner power on", voice operation unit 13 reads from storage unit 17 an operation signal for turning on air conditioner 30 associated with the voice recognition result. , to the air conditioner 30 . The air conditioner 30 receives the operation signal and turns on the power of the air conditioner 30 according to the received operation signal.

Further, when the speech recognition result indicates "playback of content title A", voice operation unit 13 stores an operation signal for instructing playback of content title A associated with the voice recognition result to storage unit 17. , and transmits it to the reproduction processing unit 14 .

The reproduction processing unit 14 performs content processing such as reproduction, stop, fast forward, rewind, etc. of the content according to the operation signal from the voice operation unit 13 . For example, the reproduction processing unit 14 reads the content data of title A indicated by the operation signal from the storage unit 17 and outputs the read content data to the video output unit 15 .

The video output unit 15 receives content data from the reproduction processing unit 14 and transmits the received content data to the display device 20 to display the content data on the screen of the display device 20 .

The hotword display control unit 16 functions as a display control unit, and performs control for displaying hotwords on the screen of the display device 20 . For example, the hotword display control unit 16 reads hotwords pre-stored in the storage unit 17 and outputs the read hotwords to the video output unit 15 .

The video output unit 15 receives hotwords from the hotword display control unit 16 and transmits the received hotwords to the display device 20 to display the hotwords on the screen of the display device 20 .

The storage unit 17 is a storage device for storing various data such as content data and hotwords, and is composed of, for example, a non-volatile memory such as a flash memory, or a magnetic storage device such as a HDD (Hard Disk Drive). be.

It is assumed that one or more hotwords are registered in advance in the storage unit 17 . The hotword may be stored in the storage unit 17 in advance by the manufacturer of the STB 10 before shipment of the STB 10, or may be determined by the user 40 after the shipment of the STB 10 and stored in the storage unit 17. There may be.

Words for voice operation by the voice operation unit 13 are registered in advance in the storage unit 17, and operation signals for the reproduction processing unit 14 or the air conditioner 30 associated with the words are also stored.

<Processing Flow of STB 10>
FIG. 2 is a flow chart showing an example of the STB processing procedure according to the embodiment of the present invention.

Referring to FIG. 2 , hotword display control unit 16 reads out one of the hotwords stored in storage unit 17 and outputs it to video output unit 15 . The hotwords may be read out in random order or in a predetermined order (for example, alphabetical order). The video output unit 15 receives the hotword from the hotword display control unit 16 and transmits the received hotword to the display device 20, thereby displaying the hotword on the screen of the display device 20 (S1). The hotword display control unit 16 displays hotwords on the screen for a predetermined period of time. For example, the hotword display control unit 16 preferably displays hotwords while the STB 10 is running. Note that the hotword display control unit 16 may, for example, display hotwords for a predetermined period of time (for example, 5 minutes) from the time the STB 10 is activated or the hotword is changed.

After that, the voice acquisition unit 11 determines whether voice data uttered by the user 40 has been acquired (S2).

If voice data has been acquired (YES in S2), the voice recognition unit 12 performs voice recognition on the acquired voice data so that the uttered voice of the hot word displayed on the screen of the display device 20 is included in the voice data. (S3).

If the voice data contains the uttered voice of the hot word, that is, if the hot word is uttered (YES in S3), the voice acquisition unit 11 waits until the voice data uttered by the user 40 is acquired. (S4).

If the voice data has been acquired (YES in S4), the voice recognition unit 12 performs voice recognition on the acquired voice data to determine whether or not the voice data contains an utterance of words for voice operation. Determine (S5).

If the voice data contains the uttered voice of the word for voice operation, that is, if the voice for voice operation is uttered (YES in S5), the voice operation unit 13 responds to the word for voice operation. The voice operation is executed by reading the operation signal from the storage unit 17 and transmitting it to the reproduction processing unit 14 or the air conditioner 30 (S6). That is, the reproduction processing unit 14 that has received the operation signal may read the content from the storage unit 17 and output it to the video output unit 15 based on the operation signal. The video output unit 15 acquires content from the reproduction processing unit 14 and displays it on the screen of the display device 20 . Also, the air conditioner 30 that has received the operation signal turns on or off the power of the air conditioner 30 or changes the set temperature based on the operation signal.

After the voice operation is performed, the hotword display control unit 16 changes the hotword by reading from the storage unit 17 a hotword different from the hotword displayed on the screen of the display device 20 (S7). . After that, the control is returned to step S1. As a result, the screen of the display device 20 displays a hot word different from the hot words that have been displayed so far.

If the voice data cannot be obtained (NO in S2), the hotword display control unit 16 determines whether or not a predetermined hotword change condition is satisfied (S8).

Also, if the voice data was acquired, but the voice data does not contain the voice of the hot word, that is, if the hot word is not spoken (NO in S3), the hot word display control unit 16 , whether or not the hotword change condition is satisfied (S8).

Furthermore, if the voice data does not contain the uttered voice of the word for voice operation, that is, if the voice for voice operation is not uttered (NO in S5), the hot word display control unit 16 It is determined whether or not the word change condition is satisfied (S8).

If the change condition is satisfied (YES in S8), hot word change processing (S7) is executed. If the change condition is not satisfied (NO in S8), hot word display processing is performed without changing the hot word. (S1) is executed.

For example, the hotword display control unit 16 determines that the change condition is satisfied if a predetermined time has passed since the hotword was changed, and that the change condition is not satisfied if the predetermined time has not passed since the hotword was changed. I judge. This allows the hotword to be changed periodically.

Further, the hot word display control unit 16 may determine whether or not the change condition is satisfied based on the hot word determination result signal received from the speech recognition unit 12 . For example, the hotword display control unit 16 satisfies the change condition when the number of times it is determined that the hotword is not uttered is equal to or greater than a predetermined threshold, and does not satisfy the change condition when the number of times is less than the predetermined threshold. can be judged. Further, when the number of consecutive determinations that the hotword was not uttered exceeds a predetermined threshold, the hotword display control unit 16 determines that the change condition is satisfied, and the number of consecutive determinations satisfies the predetermined threshold. In the case of less than, it may be determined that the change condition is not satisfied. Furthermore, the hotword display control unit 16 may use the number of times the hotword is determined to be uttered to determine whether or not the change condition is satisfied. These counts are reset to 0 when it is determined that the change conditions are met.

In addition, in the standby process (S4), if there is no voice data input for a certain period of time or longer, the process may be shifted to step S8.

Also, if only one hotword is registered in the storage unit 17, the hotword cannot be changed. Therefore, in such a case, the processing of steps S7 and S8 may be omitted.

<Operation example of the voice operation system>
FIG. 3 is a diagram showing an example of the operation of the voice operation system according to the embodiment of the invention.

As shown in FIG. 3, it is assumed that the STB 10 and the display device 20 that constitute the voice operation system 1 are installed in the home of the user 40 . It is desirable that the STB 10 and the display device 20 are installed in the same room, but if the STB 10 and the display device 20 can be connected and the STB 10 can acquire the voice data of the user 40, they are not necessarily installed in the same room. It doesn't have to be.

For example, when the user 40 powers on the STB 10, the screen of the display device 20 displays the hot word "lion". A user 40 at home can view the screen of the display device 20 . Therefore, when the user 40 utters "lion", the STB 10 can acquire the voice data of "lion". As a result, the STB 10 transitions to a state in which voice operations can be accepted.

On the other hand, a third party 50 outside the home cannot see the screen of the display device 20 . Therefore, the third party 50 cannot know the hot word "lion". For example, even if the third party 50 can remotely control the indoor smartphone 70 wirelessly connected to the smartphone 60 from the smartphone 60 outside the home, the third party 50 can output voice from the smartphone 70 . You can't know "Lion". For this reason, even if the smartphone 70 outputs some voice of the word "xxx", the STB 10 cannot be changed to a voice-operable state. Thereby, unauthorized operation by the third party 50 can be prevented.

<Effect of Embodiment>
As described above, according to the present embodiment, a hotword is displayed on the screen of display device 20, and voice operation by user 40 is permitted when the hotword displayed on the screen is spoken. Therefore, the third party 50 who cannot see the screen cannot know the hotword and cannot utter the hotword, thereby rejecting the voice operation by the third party 50. . Therefore, unauthorized voice operation by a third party 50 other than the user 40 of the STB 10 can be prevented.

The hotword display control unit 16 displays hotwords on the screen of the display device 20 for a predetermined period of time, and the speech recognition unit 12 recognizes the hotwords as uttered based on the voice data uttered during the predetermined period of time. It can be determined whether or not In other words, the voice operation can be permitted only when the hotword is spoken while the hotword is displayed on the screen. Therefore, the voice operation is not permitted based on other hotwords displayed on the screen in the past. As a result, unauthorized voice operations by the third party 50 can be further prevented.

Also, the STB 10 changes the hotword according to a predetermined change condition. Therefore, even if the hotword is disclosed to the third party 50, by changing the hotword, the unauthorized voice operation by the third party 50 can be prevented. It is also possible to reduce the possibility that the STB 10 will react to the sound of a TV commercial reading a fixed hot word and the STB 10 will start up.

Also, for example, if it is determined that the hotword has not been uttered a predetermined number of times in a row, the hotword can be changed. Therefore, when the third party 50 attempts to operate the STB 10 by, for example, outputting voice from the smartphone 70 by remote control and fails, the hotword can be changed. This prevents the STB 10 from being illegally operated by the third party 50 .

Also, the hotword can be changed each time the voice operation by the user 40 is completed. This makes it difficult for the hotword to be exposed to the third party 50 and prevents the STB 10 from being illegally operated by the third party 50 .

The hot word display control unit 16 can also select a word from a plurality of words pre-stored in the storage unit 17 and display the selected word on the screen of the display device 20 as a hot word. As a result, a speech recognition model capable of recognizing the word can be created before the STB 10 is shipped. Therefore, it is not necessary to learn the speech recognition model before the speech recognition unit 12 performs determination processing by speech recognition.

The storage unit 17 stores words determined by the user 40 , and the hot word display control unit 16 reads the words from the storage unit 17 and displays the read words on the screen of the display device 20 . can also In other words, since a word determined by the user 40 can be used as a hot word, the hot word can be freely determined, thereby making it difficult for the hot word to be exposed to the third party 50 .

[Appendix]
The voice operation device represented by the above STB 10 is specifically composed of a microprocessor, ROM (Read Only Memory), RAM (Random Access Memory), HDD (Hard Disk Drive), display unit, keyboard, mouse, etc. It may be configured as a computer system that is A computer program is stored in the RAM or HDD. The voice operation device achieves its functions by the microprocessor operating according to the computer program. Here, the computer program is constructed by combining a plurality of instruction codes indicating instructions to the computer in order to achieve a predetermined function.

Furthermore, part or all of the components that make up the voice operation device may be made up of one system LSI. A system LSI is an ultra-multifunctional LSI manufactured by integrating multiple components on a single chip. Specifically, it is a computer system that includes a microprocessor, ROM, RAM, etc. . A computer program is stored in the RAM. The system LSI achieves its functions by the microprocessor operating according to the computer program.

Further, the present invention may be a computer program that implements the method described above by a computer.

Further, according to the present invention, the computer program may be recorded in a non-transitory computer-readable recording medium such as an HDD, a CD-ROM, a semiconductor memory, or the like.

Further, according to the present invention, the computer program may be transmitted via an electric communication line, a wireless or wired communication line, a network represented by the Internet, data broadcasting, or the like.
Also, the voice operation device may be realized by a plurality of computers.

Also, part or all of the functions of the voice operation device may be provided by cloud computing. That is, part or all of the functions of the voice operation device may be realized by the cloud server. For example, in the STB 10, the function of the speech recognition unit 12 is realized by a cloud server, the STB 10 may be configured to transmit speech data to the cloud server and obtain the recognition result for the speech data from the cloud server. .

It should be considered that the embodiments disclosed this time are illustrative in all respects and not restrictive. The scope of the present invention is indicated by the scope of the claims rather than the meaning described above, and is intended to include all modifications within the scope and meaning equivalent to the scope of the claims.

1 voice operation system 10 STB (voice operation device)
11 voice acquisition unit 12 voice recognition unit (utterance determination unit)
13 Audio operation unit 14 Playback processing unit 15 Video output unit 16 Hot word display control unit (display control unit)
17 storage unit 20 display device 30 air conditioner 40 user 50 third party 60 smartphone 70 smartphone

Claims (11)

A voice operating device,
a display controller for displaying hotwords on the screen;
a voice acquisition unit that acquires voice data uttered by a user;
an utterance determination unit that determines whether or not the hot word is uttered based on the voice data;
a voice operation unit that permits voice operation by the user when it is determined that the hot word has been uttered ;
The voice operation device, wherein the screen exists at the same location as the voice operation device installed in the home . a display controller for displaying hotwords on the screen;
a voice acquisition unit that acquires voice data uttered by a user;
an utterance determination unit that determines whether or not the hot word is uttered based on the voice data;
a voice operation unit that permits voice operation by the user when it is determined that the hot word is uttered;
with
The voice operation device, wherein the display control unit randomly changes the hotword according to a predetermined change condition. a display controller for displaying hotwords on the screen;
a voice acquisition unit that acquires voice data uttered by a user;
an utterance determination unit that determines whether or not the hot word is uttered based on the voice data;
a voice operation unit that permits voice operation by the user when it is determined that the hot word is uttered;
with
The voice operation device, wherein the display control unit periodically changes the hotword according to a predetermined change condition . 4. The voice operation device according to claim 3 , wherein said display control section changes said hot word based on the determination result of said speech determination section. 5. The voice operation device according to claim 4 , wherein the display control unit changes the hotword based on the number of times the hotword is determined not to be spoken. a display controller for displaying hotwords on the screen;
a voice acquisition unit that acquires voice data uttered by a user;
an utterance determination unit that determines whether or not the hot word is uttered based on the voice data;
a voice operation unit that permits voice operation by the user when it is determined that the hot word is uttered;
with
The voice operation device, wherein the display control unit changes the hot word according to a predetermined change condition and based on the determination result of the speech determination unit. a display controller for displaying hotwords on the screen;
a voice acquisition unit that acquires voice data uttered by a user;
an utterance determination unit that determines whether or not the hot word is uttered based on the voice data;
a voice operation unit that permits voice operation by the user when it is determined that the hot word is uttered;
with
The voice operation device, wherein the display control unit changes the hotword when the voice operation ends. causing the hotword to appear on the screen;
obtaining voice data uttered by a user;
determining whether the hotword is uttered based on the audio data;
allowing voice manipulation by the user if it is determined that the hotword has been spoken ;
The voice operation method , wherein the step of displaying on the screen periodically changes the hotword according to a predetermined change condition . causing the hotword to appear on the screen;
obtaining voice data uttered by a user;
determining whether the hotword is uttered based on the audio data;
allowing the user to perform a voice operation when it is determined that the hotword has been uttered;
including
In the step of displaying on the screen, the voice operation method changes the hotword according to a predetermined change condition based on a determination result as to whether or not the hotword is uttered. causing the hotword to appear on the screen;
obtaining voice data uttered by a user;
determining whether the hotword is uttered based on the audio data;
allowing the user to perform a voice operation when it is determined that the hotword has been uttered;
including
The voice manipulation method, wherein the step of displaying on the screen changes the hotword when the voice manipulation ends. a display device;
A voice operation system comprising the voice operation device according to any one of claims 1 to 7 .

Images