JP5120158B2 - Speech recognition device, terminal device, speech recognition device program, and terminal device program - Google Patents

Description

  The present invention relates to a voice recognition apparatus that enables a terminal device in a state capable of data communication to be operated by a user's uttered voice.

Conventionally, there is a car audio system described in Patent Document 1 as an audio device that can be operated by voice recognition. In this car audio system, a user's uttered voice is input, and the input uttered voice is recognized by referring to recognition data (voice recognition dictionary) given in advance for each usable command.
JP 11-317063 A

  However, in a conventional voice recognition device, when a terminal device in a state where data communication with the voice recognition device is possible (for example, a state connected via a communication cable) is to be operated by a user's voice, it is determined in advance. If the operation is based on only the command (play, stop, fast forward, etc.) that is in progress, it will be possible immediately, but if it is possible to specify the content data stored in the terminal device, the operation is possible There was a problem that it took a long time to become.

  That is, the speech recognition apparatus has a speech recognition engine inside, and in order to execute speech recognition, a speech recognition dictionary corresponding to the speech recognition engine must be prepared in advance. If content data such as music or video is stored in the terminal device, the content data stored in the terminal device is not stored in the speech recognition device unless a speech recognition dictionary that can identify the content data is stored in advance. It cannot be specified by the user's voice.

  Since the information regarding the content data stored in the terminal device cannot be recognized on the voice recognition device side unless the terminal device and the voice recognition device are in a communicable state, data communication between the terminal device and the voice recognition device is possible. After entering the state, a speech recognition dictionary for specifying content data is created inside the speech recognition apparatus.

Therefore, after the terminal device and the voice recognition device are ready for data communication, the terminal device cannot be operated by voice recognition unless a long time elapses.
The present invention has been made to solve such a problem, and after the terminal device and the voice recognition device are ready for data communication, the terminal device can be operated by voice recognition in a short time. For the purpose.

The speech recognition apparatus of the present invention made to achieve the above object inputs a user's speech and performs speech recognition of the input speech by referring to a speech recognition dictionary stored in an internal storage device. A speech recognition device for performing dictionary acquisition means. The dictionary acquisition means stores the content data on the condition that data communication is possible with a terminal device that can be operated by a user's uttered voice in a state where the content data is stored and can be communicated with the voice recognition device. A voice recognition dictionary that can be specified by the uttered voice is acquired from the terminal device .

According to this invention, since the voice recognition dictionary is not created inside the voice recognition device but is acquired from the terminal device, the time until the terminal device can be operated by the uttered voice can be shortened.

As a terminal device, a tool for creating a speech recognition dictionary corresponding to the type of speech recognition engine possessed by the speech recognition device based on specific information that can identify the speech recognition engine type possessed by the speech recognition device is provided as an external device. As an example, a terminal device that creates the above speech recognition dictionary that can be acquired from the above, and that enables content data to be specified by spoken speech using the acquired tool can be given.
  Further, the voice recognition apparatus can be configured to include specific information transmitting means for transmitting specific information that can specify the type of the voice recognition engine of the voice recognition apparatus to the terminal device. And the dictionary acquisition means can acquire the speech recognition dictionary which can specify the said content data by speech sound corresponding to the kind of speech recognition engine which the said speech recognition apparatus has from such a terminal device. .

According to the present invention, for example, the terminal device can create a speech recognition dictionary that is suitable for the speech recognition engine of the speech recognition device, so that efficient preparation is possible without creating an unnecessary speech recognition dictionary. It becomes.

Further, the speech recognition apparatus, the dictionary acquisition means, can be configured to acquire the speech recognition dictionary to be identified in the speech content data whose content of at least one of the music and video.

According to this speech recognition apparatus, since a speech recognition dictionary that can identify content data that generally contains a large number of pieces of music or video is acquired from the terminal device , the time for creating the speech recognition dictionary can be reduced. .

A terminal device of the present invention made to achieve the above object is a terminal device in which content data is stored in an internal storage device, and includes a dictionary transmission unit. The dictionary transmitting means inputs the user's utterance voice, refers to the voice recognition dictionary stored in the internal storage device, recognizes the inputted utterance voice, and can communicate data with the terminal device. A speech recognition dictionary that enables content data to be specified by speech speech on the condition that the terminal device can be operated by the speech speech of the user in a state where data communication is possible. Send.

According to this terminal device , similarly to the above-described invention, it is possible to shorten the time until the terminal device can be operated by the uttered voice.
The above-mentioned terminal device can further be provided with specific information acquisition means. The specific information acquisition unit acquires specific information capable of specifying the type of the voice recognition engine included in the voice recognition device from the voice recognition device. And a dictionary transmission means transmits the speech recognition dictionary corresponding to the kind of speech recognition engine which a speech recognition apparatus has to a speech recognition apparatus based on the specific information acquired by the specific information acquisition means.

According to this terminal device , the same effect as that of the above-described invention can be obtained.
The terminal device can be provided with a tool acquisition unit and a dictionary creation unit. The tool acquisition means acquires from the outside a tool for creating a speech recognition dictionary corresponding to the type of speech recognition engine of the speech recognition device based on the specific information acquired by the specific information acquisition means, and the dictionary creation means using the obtained by the tool obtaining unit tool, capable of specifying the content data stored therein, to create a speech recognition dictionary corresponding to the type of speech recognition engine having the voice recognition device.

According to this terminal device , since the speech recognition dictionary is created using a tool suitable for the speech recognition engine, it is possible to improve the efficiency of the process of creating the speech recognition dictionary.

The terminal device can be configured to store at least one piece of music and videos therein as contents data. According to this terminal device , the same effect as that of the above-described invention can be obtained.

  In addition, according to the speech recognition apparatus program for causing the computer to realize the functions of each means included in the speech recognition apparatus, the computer can input speech utterances of the user and recognize the speech stored in the internal storage device. By referring to the dictionary, it is possible to function as the above-described speech recognition apparatus that performs speech recognition of the input uttered speech.

Similarly, according to the terminal device program for causing the computer to realize the functions of each means included in the terminal device, the computer can be caused to function as the above-described terminal device in which the content data is stored in the internal storage device. it can.

Embodiments to which the present invention is applied will be described below with reference to the drawings.
[1 Configuration]
FIG. 1 is a block diagram showing the overall configuration of a speech recognition system as an embodiment of the present invention. As shown in the figure, this voice recognition system includes a navigation device 1 mounted on a vehicle, an external audio device 2 that can be carried by the user, and a personal computer (hereinafter referred to as “PC”) that is used by the user to download data to the external audio device 2. 3) A server 4 in which various data such as music and tools are stored is provided.

The navigation device 1 is an electronic device that is mounted on a vehicle and performs navigation of a road or the like to the driver by an image or voice, and can be operated by a user's voice.
The external audio device 2 can select and specify content data such as music and moving images stored in advance from items such as title, artist, album, and genre by a user operation, and reproduce the content data.

The PC 3 is a general-purpose personal computer that executes various processes such as managing content data stored in the external audio device 2.
The server 4 is a server device for transmitting and receiving various data by communicating with the PC 3.

  In this voice recognition system, the external audio device 2 is in a state in which data communication with the navigation device 1 can be performed in a wired or wireless manner (for example, a state connected with a communication cable or a communication area in which short-range wireless communication is possible). In a state in which data communication is possible, content data such as music and video stored in the external audio device 2 can be specified by the user's uttered voice via the navigation device 1. It becomes like this. The external audio device 2 can be connected to the PC 3, and the PC 3 can perform data communication with the server 4 in a wired or wireless manner. The PC 3 can download content data such as music and moving images, tools for creating a speech recognition dictionary, and the like from the server 4.

  FIG. 2 is a block diagram showing an internal configuration of the navigation device 1. The navigation device 1 includes a position detector 11, an operation switch group 12, an external audio equipment connection I / F 13, a steering switch (hereinafter referred to as “steering SW”) 14, a microphone 15, a control circuit 16, a memory 17, and a display device 18. Prepare.

The position detector 11 receives a transmission radio wave from a GPS (Global Positioning System) artificial satellite via a GPS antenna, and detects the position, speed, traveling direction, and the like of the vehicle.
The operation switch group 12 includes a touch panel that is integrated with the display device 18 and is installed on the display screen, and a mechanical key switch provided around the display device 18. Note that the touch panel and the display device 18 are laminated and integrated, and there are various types of touch panels such as a pressure-sensitive method, an electromagnetic induction method, a capacitance method, or a combination thereof. It may be used.

  The external audio device connection I / F 13 is a USB (Universal / Serial / Bus) interface for connecting a portable portable music player such as the external audio device 2, for example.

The steering switch 14 is a switch group that is provided in the vicinity of the steering and is used to operate the navigation device 1, and has the same function as the operation switch group 12.
The microphone 15 is a device for inputting a user's speech voice such as a driver.

The control circuit 16 is an electronic control unit for sending control signals to various devices of the navigation apparatus 1 and executing data processing.
The memory 17 is a storage device for storing various data used in the navigation device 1 and stores information related to a speech recognition engine (acoustic recognition engine) in advance. Further, the memory 17 can receive and store a voice recognition dictionary (sound recognition dictionary) for searching for music from the external audio device 2, for example.

The display device 18 is a display for displaying a map, a music to be reproduced, and the like, and is integrated with the operation switch group 12 as described above.
FIG. 3 is a block diagram showing the internal configuration of the external audio device 2. The external audio device 2 includes an operation switch group 21, an external device connection I / F 22, a control circuit 23, a memory 24, and a display device 25.

The operation switch group 21 includes operation buttons, touch sensors, and the like, and is a switch group for operating the external audio device 2.
The external device connection I / F 22 is a USB (Universal / Serial / Bus) interface for connecting the external audio device 2 to the navigation device 1 and the PC 3 so as to communicate with each other.

  The memory 24 is a storage device for storing various data used in the external audio device 2. For example, a speech recognition dictionary (sound recognition dictionary) for searching for music, a speech recognition engine used in the navigation device 1. Information relating to the (sound recognition engine), a sound recognition dictionary creation tool (hereinafter referred to as “tool”) for creating a speech recognition dictionary, and the like can be stored.

The display device 25 is a display for displaying an operation state of the external audio device 2 and a title of content.
FIG. 4 is a block diagram showing the internal configuration of the PC 3. The PC 3 includes an operation switch group 31, an external device connection I / F 32, a network connection I / F 33, a control circuit 34, a memory 35, and a display device 36.

  The operation switch group 31 is an input device such as a keyboard or a mouse, and the external device connection I / F 32 is a USB (Universal / Serial / Bus) interface capable of connecting the external audio device 2 to the PC 3. The network connection I / F 33 is an interface for connecting to the Internet line by wire or wirelessly, and the control circuit 34 is a central control unit that sends a control signal to each device of the PC 3 and performs data processing.

  The memory 35 is a storage device that stores a tool for creating a speech recognition dictionary, information on the speech recognition engine used in the navigation device 1, and the like. The display device 36 is a display that displays a calculation result by the PC 3 and the like.

Although the internal configuration of the server 4 is not shown, it is the same as the block diagram of the PC 3 shown in FIG.
[2 processing]
Hereinafter, processing executed by the navigation device 1, the external audio device 2, the PC 3, and the server 4 according to the present embodiment will be described in order.

  FIG. 5 is a flowchart showing processing executed by the control circuit 16 of the navigation device 1. The control circuit 16 of the navigation device 1 starts this process when the user connects the external device connection I / F 22 of the external audio device 2 and the external audio device connection I / F 13 of the navigation device 1 with a cable.

  First, in S <b> 100, the control circuit 16 of the navigation device 1 determines whether information related to the speech recognition engine of the navigation device 1 (hereinafter referred to as “speech recognition engine information”) is stored in the external audio device 2. Specifically, the control circuit 16 transmits a signal for inquiring about the speech recognition engine information to the external audio device 2, and determines the presence or absence of the speech recognition engine information from the signal returned from the external audio device 2.

  The speech recognition engine information here indicates data that can specify the type of the speech recognition engine that depends on the manufacturer or model of the navigation device 1. It is possible to specify whether the engine is used. Based on this speech recognition engine information, a tool (software) for creating a speech recognition dictionary that the speech recognition engine refers to when performing speech recognition can be specified.

  If the speech recognition engine information is stored in the external audio device 2 in S100 (S100: YES), the process proceeds to S110, and if the speech recognition engine information is not stored in the external audio device 2 (S100: NO), S160. Proceed to

  In S110, it is determined whether or not the speech recognition engine information included in the navigation device 1 and the speech recognition engine information stored in the external audio device 2 are the same. That is, the control circuit 16 of the navigation device 1 receives the speech recognition engine information from the external audio device 2, and determines whether or not the information is compared with the engine information that the navigation device 1 has.

  If the speech recognition engine information of the navigation device 1 and the speech recognition engine information stored in the external audio device 2 are the same in S110 (S110: YES), the process proceeds to S120, and if not the same (S110: NO) The process proceeds to S160.

  In S120, it is determined whether or not a speech recognition dictionary (acceptance dictionary) corresponding to a song or a video stored as content data in the external audio device 2 exists (stores) in the external audio device 2. . That is, the control circuit 16 sends a signal inquiring about the presence of the speech recognition dictionary to the external audio device 2 and makes a determination based on the confirmation signal returned from the external audio device 2.

  Note that the speech recognition dictionary that supports content data such as music and videos is a feature that is necessary for speech recognition from spoken voice data that corresponds to text data such as titles, artist names, album names, and genres for normal music. The music can be specified by comparing with the voice of the user. In the following, music will be described in particular, but the same processing is applied to moving images.

  If all speech recognition dictionaries are stored corresponding to the music stored in the external audio device 2 in S120 (S120: all are present), the process proceeds to S130, and is stored in the external audio device 2 in S130. All the voice recognition dictionaries that are present are acquired by data communication, stored in the memory 17 of the navigation device 1, and the process is terminated.

  If a part of the voice recognition dictionary is stored corresponding to the music stored in the external audio device 2 in S120 (S120: a part is present), the process proceeds to S140, and stored in the external audio device 2 in S140. The acquired voice recognition dictionary is acquired by data communication, stored in the memory 17 of the navigation device 1, and the process proceeds to S150.

  In S150, in order to create a speech recognition dictionary that is not stored in the external audio device 2, the information (title, artist name album name, genre, etc.) of the remaining music stored in the external audio device 2 is used as the external audio device 2. Is acquired by data communication, and the control circuit 16 of the navigation device 1 creates a speech recognition dictionary for the remaining music, etc. (S150), and ends the process. In the process of creating a speech recognition dictionary from music information, a tool (software) for creating a speech recognition dictionary is stored in advance in the memory 17 of the navigation apparatus 1 and the control circuit 16 executes the tool. Done in How the tool creates a speech recognition dictionary uses a well-known method and will not be described in detail here.

  When the speech recognition engine information is not stored in the external audio device 2 in S100 (S100: NO), and the speech recognition engine information stored in the external audio device 2 is the speech recognition engine information of the navigation device 1 in S110. (S110: NO), the process proceeds to S160.

  In S160, the speech recognition engine information of the navigation device 1 is transmitted to the external audio device 2. That is, since information that can identify the voice recognition engine used in the navigation device 1 is not stored in the external audio device 2, the voice recognition engine information is transmitted to the external audio device 2, and the external audio device 2 side sends it to the voice recognition engine. Make it possible to create a suitable speech recognition dictionary. Specifically, the external audio device 2 acquires a speech recognition dictionary creation tool suitable for the speech recognition engine, and executes the tool. After the process of S160, the process proceeds to S170.

In S120, if there is no voice recognition dictionary corresponding to the music stored in the external audio device 2 (S120: none), the process proceeds to S170.
In S170, the music information stored in the external audio device 2 is acquired, the control circuit 16 of the navigation device 1 creates a speech recognition dictionary corresponding to the music, and the process ends.

  FIG. 6 is a flowchart illustrating processing executed by the control circuit 23 of the external audio device 2 in a state where the control circuit 23 is connected to the navigation device 1. The control circuit 23 of the external audio device 2 starts this processing when the user connects the external audio device connection I / F 13 of the navigation device 1 and the external device connection I / F 22 of the external audio device 2 by a cable.

  First, in S200, it is determined whether or not the speech recognition engine information stored in the navigation device 1 and the speech recognition engine information stored in the memory 24 of the external audio device 2 are the same. If the speech recognition engine is not stored in the memory 24, it is determined that they are not the same.

  If the speech recognition engine information stored in the navigation device 1 and the speech recognition engine information stored in the memory 24 of the external audio device 2 are the same (S200: YES), the process proceeds to S210, and if not the same (S200). : NO), the process proceeds to S250.

In S210, it is determined whether or not the corresponding speech recognition dictionary is stored in the memory 24 of the external audio device 2.
If the memory 24 stores all the speech recognition dictionaries corresponding to the music in S210 (S210: all are present), the process proceeds to S220, and all the speech recognition dictionaries stored in the memory 24 are stored in S220. To finish the process.

In S210, when some speech recognition dictionaries corresponding to the music are stored in the memory 24 (S210: some are present), the process proceeds to S230.
In S230, the speech recognition dictionary stored in the memory 24 is transmitted to the navigation device 1, and the process proceeds to S240.

  In S240, in order to create a speech recognition dictionary that is not stored in the memory 24 of the external audio device 2 on the navigation device 1 side, information of the remaining music stored in the memory 24 of the external audio device 2 is stored in the navigation device 1. Send and finish the process.

  On the other hand, if the speech recognition engine information stored in the navigation device 1 and the speech recognition engine information stored in the memory 24 of the external audio device 2 are not the same in S200 (S200: NO), the process proceeds to S250. In S250, the speech recognition engine information is acquired from the navigation device 1, and the process proceeds to S260.

In S210, if there is no voice recognition dictionary corresponding to the music stored in the memory 24 of the external audio device 2 (S210: none), the process proceeds to S260.
In S260, information such as music stored in the memory 24 of the external audio device 2 is transmitted to the navigation device 1, and the process is terminated.

  FIG. 7 is a flowchart illustrating processing executed by the control circuit 23 of the external audio device 2 in a state where the control circuit 23 is connected to the PC 3. The control circuit 23 of the external audio device 2 allows the external device connection I / F 22 of the external audio device 2 and the external device connection I / F 32 of the PC 5 to be operated by the user by voice recognition. This process is started when a program for creating a speech recognition dictionary is executed.

  First, in S300, it is determined whether or not speech recognition engine information is stored in the memory 24 of the external audio device 2. If the speech recognition engine is not stored in the memory 24 (S300: NO), the process proceeds to S310. If the speech recognition engine is stored (S300: YES), the process proceeds to S320.

In S <b> 310, all tools that can support all voice recognition engines are received from the PC 5 by communication and stored in the memory 24. Thereafter, the process proceeds to S330.
On the other hand, in S320, it is determined whether or not a tool corresponding to the speech recognition engine information stored in the memory 24 is stored in the memory 24. Specifically, the correspondence with the speech recognition engine information stored in the memory 24 is confirmed by a method such as referring to the version data of the tool stored in the memory 24. If the tool is not stored, it is determined that the corresponding tool is not stored. If the corresponding tool is stored (S320: YES), the process proceeds to S330, and if the corresponding tool is not stored (S320: NO), the process proceeds to S340.

  In S330, it is determined whether or not all speech recognition dictionaries have been created from content data such as music stored in the memory 24. If all voice recognition dictionaries have been created from the music (S330: YES), the process is terminated. If all the speech recognition dictionaries have not been created from the music or the like (S330: NO), the process proceeds to S350.

  On the other hand, in S340, a tool corresponding to the speech recognition engine information stored in the memory 24 is acquired from the PC 3 by communication and stored in the memory 24. Specifically, the voice recognition engine information is sent to the PC 3 and a corresponding tool is received from the PC 3. Thereafter, the process proceeds to S350.

  In S350, the control circuit 23 of the external audio device 2 executes the tool stored in the memory 24, creates a speech recognition dictionary based on the music information (title, artist, album, genre, etc.), and performs processing. finish. If all tools are acquired in S310, a speech recognition dictionary that can be used for all speech recognition engines is created. In this case, the control circuit 16 of the navigation device 1 selects only the speech recognition dictionary corresponding to the speech recognition engine information stored in the memory 17 of the navigation device 1 instead of the flowchart shown in FIG. Thus, the selected speech recognition dictionary is acquired.

  FIG. 8 is a flowchart showing a process executed by the control circuit 34 of the PC 3 with the external audio device 2 connected. The control circuit 34 of the PC 3 starts this processing when the user connects the external device connection I / F 32 of the PC 5 and the external device connection I / F 22 of the external audio device 2 with a cable and executes a predetermined program. To do.

  First, in S400, it is determined whether or not the same speech recognition engine information as the speech recognition engine information stored in the external audio device 2 is stored in the memory 35 of the PC 3. Specifically, the control circuit 34 of the PC 3 inquires the external audio device 2 about the voice recognition engine information, and compares the same voice recognition engine with the memory 35 to determine. If the speech recognition engine information is stored in the memory 35 (S400: YES), the process proceeds to S410. If the speech recognition engine information is not stored (S400: NO), the process proceeds to S440.

In S410, as a preparation for downloading the latest version of the tool, the old version of the unnecessary tool is deleted, and the process proceeds to S420.
In S420, the latest version of the tool is downloaded from the speech recognition engine information from the server 4, and the process proceeds to S430.

  In S430, it is determined whether or not the latest version of the tool corresponding to the speech recognition engine information is stored in the external audio device 2. Specifically, this is performed by comparing the tool downloaded in S420 with the tool stored in the external audio device 2. If the latest version is stored in the external audio device 2 (S430: YES), the process is terminated as it is. If the latest version is not stored in the external audio device 2 (S430: NO), the process proceeds to S490.

  On the other hand, if the same speech recognition engine as the speech recognition engine information stored in the external audio device 2 is not stored in the memory 35 in S400 (S400: NO), the process proceeds to S440, and in S440, the external audio device A command to acquire voice recognition engine information is sent to 2, and the process proceeds to S450.

  In S450, it is determined whether or not the speech recognition engine information has been acquired from the external audio device 2. If the speech recognition engine information can be acquired (S450: YES), the process proceeds to S410. If the speech recognition engine information cannot be acquired (eg, the speech recognition engine information is not stored in the external audio device 2) (S450: NO), the process proceeds to S460.

In S460, in preparation for downloading the latest version of the tool, the unnecessary tool of the old version is deleted, and the process proceeds to S470.
In S470, the tool about all the speech recognition engines is downloaded from the server 4, and it progresses to S480.

  In S480, it is determined whether or not the latest version of the tool corresponding to all the speech recognition engine information is stored in the external audio device 2. If the latest versions of all the tools are stored (S480: YES), the process is terminated as it is. If the latest version of the tool is not stored (S490: NO), the process proceeds to S490.

In S490, the latest version of the tool is transmitted from the PC 3 to the external audio device 2, and the process ends.
FIG. 9 is a flowchart showing a process executed when a control circuit (not shown) of the server 4 communicates with the PC 3. The control circuit of the server 4 starts processing upon access from the PC 3.

First, in S500, an access request signal from the PC 3 is received, and the process proceeds to S510.
In S510, it is determined whether or not the voice recognition engine information of the navigation device 1 has been acquired from the PC 3. If the speech recognition engine information can be acquired (S510: YES), the process proceeds to S520. If the speech recognition engine information cannot be acquired (S510: NO), the process proceeds to S540.

  In S520, it is determined whether or not the latest version of the tool stored in the server 4 matches the tool stored in the PC 3. Specifically, for example, tool information (version information) is acquired from the PC 3. In this case, if the tool is not stored in the tool, the PC 3 determines that the two do not match. If the two match (S520: YES), the process ends. If the two do not match (S520: NO), the process proceeds to S530.

In S530, the tool corresponding to the speech recognition engine information requested by the PC 3 from the server 4 is distributed to the PC 3, and the process is terminated.
In S540, all the tools that can support all voice recognition engines are distributed from the server 4 to the PC 3, and the process ends.

[3 effects]
As described above, according to the speech recognition system of the present embodiment, the speech recognition dictionary is not created inside the navigation device 1 but is created after it is created inside the external audio device 2, so that the external audio device 2 speaks the speech voice. Thus, the time until the operation becomes possible can be shortened.

Moreover, since the speech recognition dictionary generally corresponds to content data that contains a large number of pieces of music or moving images, the effect of shortening the time is extremely great.
Further, since the speech recognition engine information stored in the navigation device 1 is sent to the external audio device 2 and a speech recognition dictionary is created using a tool suitable for the speech recognition engine, it is not necessary when this operation is performed. Efficient preparation is possible without creating a speech recognition dictionary.

[4 Correspondence with Claims]
In the navigation device 1 of the present embodiment, the control circuit 16 that executes S130 and S140 corresponds to a dictionary acquisition unit, and the control circuit 16 that executes S160 corresponds to a dictionary transmission unit.

  For the external audio equipment 2, the control circuit 23 that executes S220 and S230 corresponds to the dictionary transmission means, the control circuit 23 that executes S250 corresponds to the specific information acquisition means, and the control circuit 23 that executes S340 acquires the tool. The control circuit 23 that executes S350 corresponds to the dictionary creation means.

[5 Other forms]
As mentioned above, although one Embodiment of this invention was described, it cannot be overemphasized that this invention can take a various form.

  For example, in the present embodiment, the external audio device 2 is configured to download data such as music, moving images, and tools from the PC 3. However, for example, a device such as a mobile phone or a communication portable terminal can be used without going through the PC 3. Alternatively, a configuration may be adopted in which various data are downloaded by directly connecting to the Internet or a server in the center by wireless.

  In this embodiment, the voice recognition dictionary is created by executing the tool inside the external audio device 2. However, for example, the tool may be executed by the PC 3 or the voice recognition dictionary created in advance by the server 4 may be used. You may make it the structure received by download etc.

  Further, in the present embodiment, the case where the music data is particularly set as the content data has been described. However, the video data may be a movie, a file such as a word processor, a spreadsheet, a slide for presentation, audio data such as a game, news, lecture, entertainment, Any content data such as image data such as a photograph taken with a digital camera may be used.

1 is a block diagram showing an overall configuration of a speech recognition system as an embodiment of the present invention. It is a block diagram which shows the internal structure of a navigation apparatus. It is a block diagram which shows the internal structure of an external audio apparatus. It is a block diagram which shows the internal structure of a personal computer. It is a flowchart which shows the process which the control circuit of a navigation apparatus performs. It is a flowchart which shows the process which the control circuit of an external audio equipment performs in the state connected to the navigation apparatus. It is a flowchart which shows the process which the control circuit of an external audio equipment performs in the state connected to the personal computer. It is a flowchart which shows the process which the control circuit of a personal computer performs in the state which connected the external audio equipment. It is a flowchart which shows the process performed when the control circuit of a server communicates with a personal computer.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Navigation apparatus, 2 ... External audio equipment, 3 ... PC, 4 ... Server, 11 ... Position detector, 12 ... Operation switch group, 13 ... External audio equipment connection I / F, 14 ... Steering SW, 15 ... Microphone, DESCRIPTION OF SYMBOLS 16 ... Control circuit, 17 ... Memory, 18 ... Touch panel, 21 ... Operation switch group, 22 ... External apparatus connection I / F, 23 ... Control circuit, 24 ... Memory, 25 ... Display apparatus, 31 ... Operation switch group, 32 ... External device connection I / F, 33 ... Network connection I / F, 34 ... Control circuit, 35 ... Memory, 36 ... Display device

Claims (6)

A speech recognition device for inputting speech of a user and performing speech recognition of the input speech by referring to a speech recognition dictionary stored in an internal storage device,
Specific information that can identify the type of voice recognition engine of the voice recognition device, which is a terminal device that can be operated by a user's uttered voice in a state where content data is stored and data communication with the voice recognition device is possible Based on the above, a tool for creating a speech recognition dictionary corresponding to the type of speech recognition engine that the speech recognition apparatus has is acquired from the outside, and the content data can be specified by uttered speech using the acquired tool Voice recognition that enables the content data corresponding to the type of voice recognition engine of the voice recognition device to be specified by speech voice on condition that data communication is possible with a terminal device that creates the voice recognition dictionary Dictionary acquisition means for acquiring a dictionary from the terminal device ;
Specific information transmitting means for transmitting the specific information capable of specifying the type of the voice recognition engine of the voice recognition device to the terminal device;
A voice recognition device characterized by comprising: 2. The speech recognition apparatus according to claim 1 , wherein the dictionary acquisition unit acquires a speech recognition dictionary that enables content data containing at least one of music and moving images to be specified by speech. A terminal device in which content data is stored in an internal storage device,
The user's speech is input, the speech recognition of the input speech is performed by referring to the speech recognition dictionary stored in the internal storage device, and the terminal device is placed in a state where data communication with the terminal device is possible. A speech recognition dictionary that the speech recognition device has a speech recognition dictionary that allows the content data to be specified by speech speech on condition that data communication is possible with a speech recognition device that can be operated by speech speech of a user Dictionary transmitting means for transmitting a speech recognition dictionary corresponding to the type of the speech recognition device to the speech recognition device ;
Specific information acquisition means for acquiring, from the voice recognition device, specific information capable of specifying the type of voice recognition engine of the voice recognition device;
Based on the specific information acquired by the specific information acquisition means, a tool acquisition means for acquiring a tool for creating a voice recognition dictionary corresponding to the type of voice recognition engine of the voice recognition device from the outside,
Using the tool acquired by the tool acquisition means, a dictionary creation means for creating the speech recognition dictionary corresponding to the type of speech recognition engine of the speech recognition device;
A terminal device characterized by comprising: 4. The terminal device according to claim 3 , wherein the terminal device stores content data containing at least one of music and a moving image in a storage device inside the terminal device. A program for a speech recognition device for causing a computer to function as a speech recognition device for inputting speech of a user and referring to a speech recognition dictionary stored in an internal storage device to perform speech recognition of the input speech speech. There,
Specific information that can identify the type of voice recognition engine of the voice recognition device, which is a terminal device that can be operated by a user's voice in a state where content data is stored and data communication with the voice recognition device Based on the above, a tool for creating a speech recognition dictionary corresponding to the type of speech recognition engine that the speech recognition apparatus has is acquired from the outside, and the content data can be specified by uttered speech using the acquired tool Voice recognition that enables the content data corresponding to the type of voice recognition engine of the voice recognition device to be specified by speech voice on condition that data communication is possible with a terminal device that creates the voice recognition dictionary Dictionary acquisition means for acquiring a dictionary from the terminal device ;
Specific information transmitting means for transmitting the specific information capable of specifying the type of the speech recognition engine of the speech recognition apparatus to the terminal device
A program for a speech recognition apparatus for causing a computer to function as a computer. A program for a terminal device for causing a computer to function as a terminal device whose content data is stored in an internal storage device,
The user's speech is input, the speech recognition of the input speech is performed by referring to the speech recognition dictionary stored in the internal storage device, and the terminal device is placed in a state where data communication with the terminal device is possible. A speech recognition dictionary that the speech recognition device has a speech recognition dictionary that allows the content data to be specified by speech speech on condition that data communication is possible with a speech recognition device that can be operated by speech speech of a user Dictionary transmitting means for transmitting a speech recognition dictionary corresponding to the type of the speech recognition device to the speech recognition device ;
Specific information acquisition means for acquiring, from the voice recognition device, specific information capable of specifying the type of voice recognition engine of the voice recognition device;
Based on the specific information acquired by the specific information acquisition means, a tool acquisition means for acquiring a tool for creating a voice recognition dictionary corresponding to the type of voice recognition engine of the voice recognition device from the outside,
A program for a terminal device for causing a computer to function as a dictionary creation unit that creates the speech recognition dictionary corresponding to the type of speech recognition engine of the speech recognition apparatus using the tool acquired by the tool acquisition unit .

Images