JP5361781B2 - On-vehicle electronic device and voice data dictionary generation method for music data - Google Patents

Description

  The present invention relates to an on-vehicle electronic device, and more particularly to an on-vehicle electronic device having an audio playback function that enables music selection based on a voice instruction and a method for generating a voice recognition dictionary for the music data.

  2. Description of the Related Art In recent years, in-vehicle electronic devices such as in-vehicle AV (Audio Visual) devices and navigation devices equipped with AV playback functions are becoming more and more functional. With regard to the music playback performance, a technique called voice song search (or also called SBV (Song By Voice)) that makes music selection by the user's voice has been adopted, and driving is deprived of vision. Because it is highly convenient for drivers, further spread is expected.

  In order to realize music selection by voice music search, it is necessary to generate a voice recognition dictionary in advance based on meta information stored in music data. Depending on the number of music data stored in a mass storage device such as an HDD (Hard Disk Drive) built in the electronic device, it takes a minute to complete the dictionary generation for all music. . Normally, when a music CD (Compact Disc) is inserted into an in-vehicle electronic device, the music data stored therein is ripped to the built-in HDD in the background in parallel with the reproduction, so that a new music CD is reproduced. Every time, a voice recognition dictionary is generated by voice music search.

  On the other hand, with the popularization of mp3 (MPEG Audio Layer-3: a type of compressed audio file format for digital audio) etc., you can listen to music with a portable music player, or use a USB memory (Universal Serial Bus memory: USB standard) In general, music data is stored and carried in an auxiliary storage device (which can be connected to an electronic device via the interface). For this reason, some in-vehicle electronic devices in recent years have an interface for connecting these external data storage devices so that music data stored therein can be read out and reproduced on the device side. When generating music data in such an external device, music selection by the audio music search is desired. Therefore, on the electronic apparatus side, this type of external device is connected and the device is used as a playback medium. If selected, it is necessary to generate a speech recognition dictionary prior to reproduction.

  Conventionally, the generation of this speech recognition dictionary has the following problems. That is, when a user tries to play an external device such as a portable music player while a voice recognition dictionary is being generated for music data stored in the built-in HDD, the system is built-in. After generation of the voice recognition dictionary for the music data of the HDD is completed, generation of the voice recognition dictionary for the music data of the connected external device is started. Therefore, depending on the progress of dictionary generation for music data stored in the built-in HDD, there arises a problem that it takes a minute order before the use of voice music search for music data in the external device can be started. In addition, even when a music CD is inserted and reproduction is desired while generating a music data dictionary in the external device, the data ripped in the HDD after the music data dictionary generation in the external device is completed. Since dictionary generation is performed, there is also a problem that in this case, it takes time to use voice music search for music data desired to be reproduced.

  A technique for shortening the time required for voice recognition for navigation in relation to this case is described in Patent Document 1. That is, Patent Document 1 discloses a technique for reducing the search time for one dictionary by dividing recognition target vocabulary into multiple stages according to its importance.

Japanese Patent Laid-Open No. 10-62199

  However, this technology reduces the number of vocabulary in one dictionary and shortens the dictionary search time at the time of voice input, and is used to shorten the generation time for dictionary generation that is a problem in this case. I can't do it.

  The present invention has been made in view of the above-mentioned problems, and reduces the time for generating a speech recognition dictionary required for music selection by voice music search so that the vehicle electronic device can be used quickly. An object of the present invention is to provide a method for generating a speech recognition dictionary for the music data.

  An in-vehicle electronic device according to the present invention connects an audio playback unit that enables music selection based on an instruction by voice, a music data storage unit that stores a large number of music data, and an external device that stores the music data. A voice recognition dictionary for selecting the music piece from the external device connection means for enabling the audio data to be read by the audio playback means, the music data in the music data storage means, and the music data in the external device. A voice recognition dictionary generating means for generating, a dictionary generation progress measuring means for measuring a dictionary generation progress in music data storage device units in the voice recognition dictionary generating means, and music data of one music data storage device When the voice recognition dictionary is generated, the voice recognition dictionary for the music data of other music data storage devices Priority device determining means for preferentially determining a music data storage device for generating a speech recognition dictionary according to the dictionary generation progress by the dictionary generation progress measuring means when a generation request is made; and the priority device Device switching means for causing the music data storage device determined by the determining means to be processed preferentially by the voice recognition dictionary generating means;

  Preferably, the priority device determination unit determines that a request for generating a speech recognition dictionary for the data storage device has been made when an external device storing music data is connected to the external device connection unit, A device for storing music data for generating a voice recognition dictionary is determined. Preferably, the priority device determination unit is configured to generate a voice recognition dictionary for the data storage device when a music data storage device is selected as a target of music data playback by the audio playback unit. It is determined and a storage device for music data for preferentially generating a speech recognition dictionary is determined.

  Preferably, the priority device determination means puts a music data storage device other than that determined to preferentially generate a voice recognition dictionary into a queue for requesting dictionary generation by the voice recognition dictionary generation means, After the processing in the prioritized music data storage device is completed, the devices placed in the queue are sequentially set as a dictionary generation target.

  The dictionary generation progress measuring means preferably includes an expected dictionary generation time required for processing music data in the target music data storage device based on an average processing time of unit music data by the music recognition dictionary generating means, and a dictionary The degree of progress is measured from the elapsed time from the start of the generation process.

  The present invention also connects an audio playback means that enables music selection based on a voice instruction, a music data storage means that stores a large number of music data, and an external device that stores the music data. Is a voice recognition dictionary generation method for music data in a navigation device having external device connection means that enables the audio playback means to be read from the music data in the music data storage means and the music data in the external device. A step of generating a voice recognition dictionary for music selection, a step of measuring a dictionary generation progress for each music data storage device in the generation of the voice recognition dictionary, and music data of one music data storage device. When a speech recognition dictionary is being generated for other music data storage devices Determining a music data storage device that preferentially generates a speech recognition dictionary according to the progress of dictionary generation when a request for generating a speech recognition dictionary for music data is made; and the determined music data And switching the storage device so that the generation of the voice recognition dictionary of the music data is prioritized.

  According to the present invention, even when a dictionary generation request for another music data storage device is made during generation of a speech recognition dictionary for one music data storage device, priority is given to dictionary generation according to the progress of the generation. Since a device to be determined is determined and switched as necessary, it is possible to generate a speech recognition dictionary for the required music data in a short time. As a result, the waiting time of the user related to dictionary generation is shortened, and the convenience is enhanced.

It is a block diagram which shows the structural example of the navigation apparatus which concerns on the Example of this invention. It is a functional block diagram of the main characteristic parts of the control part 124 of a present Example. It is a flowchart which shows a speech recognition dictionary production | generation process. It is a flowchart which shows a speech recognition dictionary production | generation process. It is a comparison graph for verifying the effect in the dictionary generation request process which concerns on a conventional structure, and the dictionary generation request process which concerns on a present Example.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the present embodiment, a navigation apparatus having an audio playback function that enables music selection based on a voice instruction and other multimedia functions will be exemplified.

  FIG. 1 is a block diagram illustrating a configuration example of a navigation device according to an embodiment of the present invention. As shown in the figure, a navigation device 100 includes an audio / video (AV) reproducing unit 102 that reproduces music data and video data, a terrestrial digital television broadcast, and a television / radio tuner that receives radio broadcasts such as AM and FM. 104, navigation unit 106 for route guidance to a destination, CD / DVD reading unit 108 for reading a CD or DVD (Digital Versatile Disc) storing music and other data into the system, portable music player, USB memory, etc. An external device connection interface 110 for connecting external devices, an input unit 112 for receiving input from the user via a touch panel on the display and operation buttons, and a voice input unit for receiving operation commands and music selection instructions from the user by voice 114, speaker? An audio output unit 116 for outputting audio, an information display unit 118 for displaying an image on a display, HDD 120 for storing road map data and program data, and music data ripped from a music CD, and programs and various data read from the HDD 120 A main memory 122 that temporarily stores these for execution and processing, and a control unit 124 that controls each unit are configured. The configuration of the navigation device 100 in FIG. 1 is an exemplification, and may not include all of these functions, or may include other functions.

  The audio / video playback unit 102 plays back audio data and video data stored in a CD, DVD, semiconductor memory, HDD 120, or the like. As will be described later, the audio / video playback unit 102 can play back a designated song based on a voice instruction for song selection by the user from the voice input unit 116. The reproduced audio data and video data are output from the audio output unit 116 and the information display unit 118 by the control unit 124.

  The TV / radio tuner 104 receives a terrestrial digital broadcast program of the channel selected by the control unit 124, decodes the received TV broadcast streaming data in real time, and from there, audio data, video data, electronic program information Extract text data such as (EPG) or character data. The control unit 124 receives these signals from the TV tuner 104, causes the audio output unit 116 to output a program audio signal, and causes the information display unit 118 to display the program video signal. The television / radio tuner 104 receives the radio broadcast of the channel selected by the control unit 124, decodes the received radio broadcast, and extracts stereo or monaural audio data, multiplexed character data, and the like. The extracted audio data is output from the audio output unit 116.

  The navigation unit 106 calculates the position of the own vehicle using a GPS satellite or a self-contained navigation sensor, or guides the optimum route to the destination. When the navigation unit 108 is operated, the control unit 124 causes the information display unit 118 to display a road map around the vehicle position. Also, voice guidance regarding navigation is output from the voice output unit 116.

  The CD / DVD reading unit 108 reads a CD storing music and other data, and a DVD storing video data and map data so that the audio / video playback unit 102 can play them back and use them by the navigation unit 108. When the CD / DVD reader 108 reads the CD storing the music data, the controller 124 rips the music data to the HDD 120 simultaneously with the reproduction.

  The external device connection interface 110 connects an external device such as a portable music player or a USB memory so that music and other data stored therein can be read out on the system. When the data stored in these external devices is music data, the music data is subject to playback by the audio / video playback unit 102 in accordance with a user's selection instruction. As will be described later, these music data are also read out to generate a voice recognition dictionary so that music selection instruction by voice input is possible for these music data.

  The input unit 112 can include input means such as a remote controller, a mouse, and a touch panel. The user can control music playback, select a TV broadcast channel, select a function to be operated, and give other necessary instructions via the input unit 112. The input unit 112 includes an utterance button installed around the handle in order to notify the system side of the start and end of voice input by the voice input unit 114.

  The voice input unit 114 receives voice operation commands and music selection instructions from the user. In response to a music selection instruction related to the reproduction of music data, the audio input unit 114 receives a song designation (usually a song name) from the user, which is processed by a music selection control to be described later. Playback is performed by the video playback unit 102. The voice input unit 114 includes a small microphone installed around the handle to pick up the driver's voice.

  The audio output unit 116 amplifies the audio signal, and outputs the amplified audio signal from a speaker arranged in the vehicle. The information display unit 118 includes a display for displaying still images and moving images. Further, the display is equipped with a touch panel as one means of the input unit 112 so that it can receive input from the user.

  The HDD 120 is a mass storage device that stores data relating to road maps, program data, and music data ripped from a music CD. The HDD 120 also stores voice recognition dictionary data generated by a voice recognition dictionary generation unit described later. Regarding the music data, when the music CD is inserted into the CD / DVD reading unit 106 and reproduction thereof is started, the HDD 120 stores and accumulates all the music data here. This eliminates the need for the user to cause the CD / DVD reader 106 to read the music CD again when reproducing the same music again. In recent years, the price of mass storage devices using a nonvolatile semiconductor memory such as an SSD (Solid State Drive) has been reduced. A storage device using the medium may be used.

  The main memory 122 is a storage area that temporarily holds a program selected based on a user operation or the like and data to be controlled by the program, and is usually configured by a volatile semiconductor memory. The control unit 124 includes devices such as a central processing unit, a microcomputer, and a microprocessor, executes a program read to the main memory 122, and controls each unit.

  Next, FIG. 2 shows a functional block diagram of main features of the control unit 124 of this embodiment. Here, only control related to generation of a speech recognition dictionary for music selection will be described here, and other functions in the system will not be described. The control unit 124 includes a voice command analysis unit 200, a voice recognition dictionary generation unit 202, a dictionary generation progress measurement unit 204, a priority device determination unit 206, and a device switching unit 208 as functional configurations according to the present invention.

  The voice command analysis unit 200 analyzes voice input by the user and outputs corresponding text data. The user's voice picked up through the small microphone is subjected to processing such as noise removal, normalization, and digitization by the voice input unit 114 and input to the voice command analysis unit 200. The voice command analysis unit 200 uses a well-known method related to voice recognition, such as performing an acoustic analysis and extracting a feature value therefrom, and obtaining text data from the feature value in a recognition decoder. When the use of the audio / video playback unit 102 is selected by the user, the voice command analysis unit 200 understands the acquired voice signal as a song name for song selection. Then, using this as a key, the voice recognition dictionary is searched to read the matching music data from the HDD 120, and the result is returned to the control unit 124 so as to be played back by the audio / video playback unit 102.

  The voice recognition dictionary generation unit 202 generates a voice recognition dictionary for selecting a song by voice based on the song name and other meta information included in the music data. When a request for generating a speech recognition dictionary for a music data group stored in the HDD 120 or an external device is transmitted from the control unit 124, the speech recognition dictionary generating unit 202 reads the target device (this is referred to as a music data storage device in this document). The music data is sequentially read out, and a voice recognition word (for example, a song name) for calling the music data is extracted from the meta information included therein, and associated with the target device. A dictionary is generated by storing in a predetermined area.

  Here, the voice recognition dictionary generation request is made, for example, when the audio / video playback unit 102 is selected as a control target by the user in a state where a music CD is set in the CD / DVD reading unit 108, or playback thereof is started. Can be configured to be sent when In addition, it can be configured to be transmitted when an external device such as a portable music player is connected to the external device connection interface 110 or when reproduction is started. As a result, while a dictionary generation request for one music data storage device (for example, HDD 120) is made and a voice dictionary is generated in the voice recognition dictionary generation unit 202, a dictionary for another music data storage device (portable music player) is generated. There are cases where generation requests are sent and generation requests collide.

  Further, even when a function other than the audio / video playback unit 102 (for example, the TV / radio tuner 106 or the navigation unit 108) is selected as the control target, the internal or external HDD 120 or the outside at regular intervals in the CPU idle time, etc. It is also possible to scan the inside of the device, detect music data that has not been generated in the dictionary, and generate the data. Here, when music data in which a dictionary is not generated is detected in a plurality of devices, with respect to the priority of the dictionary generation, a method that prioritizes a device with a small number of music data, a method that prioritizes the last selected device, and Any method of giving priority to the inside of the HDD 120 may be adopted. In any case, the speech recognition dictionary is generated for each device and managed independently.

  The dictionary generation progress measurement unit 204 measures the progress after the dictionary generation request is made to a specific music data storage device. Here, the degree of progress refers to the rate of progress relative to the time required to complete the speech recognition dictionary for all music data stored in the target device. As an example, the expected dictionary generation time is obtained from the average processing time required for standard unit music data and the number of music data stored in the target device, and is compared with the elapsed time from the start of the dictionary generation processing. As a result, the degree of progress can be calculated. As another example, the estimated remaining time until the completion of processing can be used as the progress.

  The priority device determination unit 206 determines a device to be preferentially processed when a voice recognition dictionary generation request conflicts between different music data storage devices. That is, the priority device determination unit 206, when a voice recognition dictionary is generated for music data of one music data storage device (for example, HDD 120), music of another music data storage device (for example, portable music player). When a voice recognition dictionary generation request for data is made, the progress degree measured by the dictionary generation progress degree measurement unit 204 is referred to and compared with a reference value to determine a priority device. As an example, if the dictionary generation for the device being processed is a progress within 30% of the required total processing time, it is determined to give priority to the processing of other music data storage devices. In consideration of the other parameters, for example, the amount or number of music data stored in the music data storage device, if the data amount or number is small and the time required for dictionary generation is expected to be short, You can also decide to prioritize devices. In addition, by setting the progress reference value to 100%, it is possible to control to always give priority to a device that has received a request when a generation request conflicts.

  Based on the determination by the priority device determination unit 206, the device switching unit 208 switches the target device for performing the speech recognition dictionary generation process. That is, if the device to be prioritized in the priority device determination unit 206 is different from the device that is currently generating the dictionary, the processing in the device that is generating the dictionary is interrupted, and this device is added to the queue for generating a dictionary, Next, the processing is switched so that the music data in the prioritized device becomes the target for generating the speech recognition dictionary.

  Next, speech recognition dictionary generation processing in the navigation device according to the present embodiment will be described with reference to the flowchart shown in FIG. In the description, during the generation of the voice recognition dictionary for the music data stored in the HDD 120, an external device storing the music data is connected to the external device connection interface 110, whereby the voice recognition for the music data of the external device is performed. An example of a case where a dictionary generation request is made will be mainly described.

  This process 300 is started by a voice recognition dictionary generation request to the voice recognition dictionary generation unit 202 of the control unit 124. In the first step, the expected dictionary generation time for all music data stored in the target device is calculated (step 301). Next, it is determined whether dictionary generation processing has already been performed for another device (step 302). If it is determined that dictionary generation has not been performed, the processing moves to step 307, and the device related to the dictionary generation request The process of generating a speech recognition dictionary for the music data is started.

  On the other hand, if it is determined that a dictionary has already been generated for another device, steps 303 to 306 for resolving the conflict are performed. Here, first, information is acquired from the system which device is currently selected by the user, that is, which function is active in the navigation device (step 303). Then, it is determined whether or not the device for which the dictionary generation request is made is the device selected by the user (step 304). If a dictionary generation request is made for a device other than the device selected by the user, it is not necessary to generate the dictionary immediately, so add the device related to the dictionary generation request to the dictionary generation request queue. (Step 313).

  On the other hand, if a dictionary generation request is made for the device selected by the user, the process proceeds to step 305 where the progress of dictionary generation already started for other devices is determined. That is, it is determined whether the elapsed time from the start of the dictionary generation is within a predetermined value (for example, 30% of the time until the process is completed). If so, it is determined that the start of the process for the requesting device is delayed. Then, the dictionary generation process for the music data of the external device that is currently progressing is stopped (step 306), and instead, the dictionary generation for the music data of the device that has been requested to generate is started immediately (step 307). Here, the device to be canceled is added to the dictionary generation request queue (step 313).

  When generation of a speech recognition dictionary for music data stored in the device related to the dictionary generation request is started, a timer is started and measurement of the dictionary generation time is started (step 308). Used in When dictionary generation for all music data included in the device is completed (step 309), the dictionary generation time measurement is terminated (step 310), and the control unit 124 completes dictionary generation from the speech recognition dictionary generation unit 202. A notification is acquired (step 311). Upon receiving this notification, the control unit 124 notifies the user of a notification that the operation by voice recognition for the target device is possible via the information display unit 118 (step 312).

  Then, the process moves to step 314 to determine whether there is a device waiting for dictionary creation. When step 313 is executed and the device related to the request is registered in the dictionary generation request queue, the first device is taken out from the queue (step 315), and this processing 300 for the device is newly started. . This target device includes a device whose processing has been stopped in the previous processing. In such a case, processing for the remaining music data is resumed. This process is repeated until there are no registered devices in the queue, and the process ends when there are no more target devices.

  FIG. 4 is a comparison graph for verifying the effects of the dictionary generation request process according to the conventional configuration and the dictionary generation request process according to the present embodiment. The graph compares the processing time when a dictionary generation request for music data of an external device is made when the process of generating a speech recognition dictionary for music data stored in the built-in HDD is performed. FIG. 5A shows a process according to the conventional configuration, and considers a case where dictionary generation processing for the internal HDD is started at the Hs point and a processing request is made for an external device at the R point. In this case, the processing request is temporarily put on hold, and when the processing for the internal HDD is completed at the He point, the processing for the external device is started (Es point). Then, at the point Ee at which the processing for the external device is completed, the music selection function by the audio music search can be used for the music data of the external device related to the request. Therefore, the time from when the generation request is made until it can be used is t1.

  On the other hand, in the process in the present embodiment shown in FIG. 5B, if a processing request for an external device is made at point R during dictionary generation for the internal HDD, if the progress is within a predetermined value, the processing for the internal HDD is performed. Is stopped and processing for the external device is immediately started (Es point). Then, after the processing for the external device is completed at the point Es, the processing for the internal HDD is resumed. Therefore, the time from when the dictionary generation request is made to the external device until it can be used is t2. As a result, in the night process of the present embodiment, the time until the music selection in the external device becomes possible is shortened by t3 as compared with the conventional configuration.

  The preferred embodiments of the present invention have been described in detail above. However, the present invention is not limited to the specific embodiments, and various modifications and changes can be made within the scope of the gist of the invention described in the claims. It can be changed.

DESCRIPTION OF SYMBOLS 100: Navigation apparatus 102: AV reproduction part 104: Television / radio tuner 106: Navigation part 108: CD / DVD reading part 110: External device connection interface 112: Input part 114: Audio | voice input part 116: Audio | voice output 118: Information display part 120: HDD 122: main memory 124: control unit 200: voice command analysis unit 202: voice recognition dictionary generation unit 204: dictionary generation progress measurement unit 206: priority device determination unit 208: device switching unit

Claims (11)

An audio playback means that enables music selection based on voice instructions;
Music data storage means for storing a large number of music data;
An external device connection means for connecting an external device storing music data and enabling the music playback means to read the music data;
Voice recognition dictionary generating means for generating a voice recognition dictionary for music selection from music data in the music data storage means and music data in the external device;
Dictionary generation progress measuring means for measuring dictionary generation progress in units of music data storage devices in the voice recognition dictionary generating means;
When a voice recognition dictionary is generated for the music data of one music data storage device and the voice recognition dictionary is generated for the music data of another music data storage device, the dictionary generation progress degree Priority device determination means for determining a storage device for music data for preferentially generating a speech recognition dictionary according to the progress of dictionary generation by the measurement means;
Device switching means for causing the music data storage device determined by the priority device determining means to be processed preferentially by the voice recognition dictionary generating means;
An electronic device. The priority device determination means determines that a request for generating a speech recognition dictionary for the other music data storage device has been made when an external device that stores music data is connected to the external device connection means. The electronic apparatus according to claim 1, wherein a device for storing music data for generating a voice recognition dictionary is determined. The priority device determination means determines that when a music data storage device is selected as a reproduction target of music data by the audio reproduction means, a request for generating a speech recognition dictionary for the music data storage device has been made, The electronic apparatus according to claim 1, wherein a storage device for music data for preferentially generating a speech recognition dictionary is determined. The priority device determination means puts music data storage devices other than those determined to generate a speech recognition dictionary with priority into a queue for requesting dictionary generation by the speech recognition dictionary generation means, and gives priority to music. The electronic apparatus according to claim 1, wherein after the processing in the data storage device ends, the devices placed in the queue are sequentially subjected to dictionary generation. The dictionary generation progress measuring means is based on an average processing time of unit music data by the speech recognition dictionary generating means, and an expected dictionary generation time required for processing music data in the target music data storage device, and starting dictionary generation processing The electronic device according to claim 1, wherein the degree of progress is measured from an elapsed time from the time. An audio playback unit that enables music selection based on an instruction by voice, a music data storage unit that stores a large number of music data, and an external device that stores music data are connected to the audio playback unit. A speech recognition dictionary generation method for music data in a navigation device having external device connection means for enabling reading
Generating a voice recognition dictionary for music selection from music data in the music data storage means and music data in the external device;
Measuring the degree of dictionary generation progress in units of music data storage devices in generating the voice recognition dictionary;
When a voice recognition dictionary is generated for the music data of one music data storage device and the voice recognition dictionary is generated for the music data of another music data storage device, the dictionary generation progress degree And determining a music data storage device that preferentially generates a speech recognition dictionary;
Switching the determined music data storage device so that the generation of a voice recognition dictionary of the music data is prioritized;
A speech recognition dictionary generation method for music data in an electronic device having The step of determining a music data storage device that preferentially generates a voice recognition dictionary includes the step of determining a voice to the other music data storage device when an external device that stores music data is connected to the external device connection means. The method for generating a speech recognition dictionary for music data in an electronic device according to claim 6, wherein it is determined that a request for generating a recognition dictionary has been made, and a storage device for music data that preferentially generates a speech recognition dictionary is determined. . Determining a storage device of the music data for generating the preferentially speech recognition dictionary, when one music data storage device for playback of the music data by the audio reproducing means is selected, the music data storage device 7. A music data speech recognition dictionary in an electronic apparatus according to claim 6, wherein a music data storage device that preferentially generates a voice recognition dictionary is determined by determining that a voice recognition dictionary generation request has been made. Generation method. Determining a storage device of the music data for generating the preferentially speech recognition dictionary, preferentially the music data storage devices other than the determination is made to generate a speech recognition dictionary, request the generation of the voice recognition dictionary The queued device is sequentially set as a dictionary generation target after the processing in the prioritized music data storage device is completed. A method for generating a speech recognition dictionary of music data in the electronic device according to claim 1. The step of measuring the progress of dictionary generation includes the expected dictionary generation time required for processing music data in the target music data storage device based on the average processing time of unit music data required for generating the voice recognition dictionary, and the dictionary The method for generating a speech recognition dictionary for music data in an electronic device according to claim 6, wherein the progress is measured from the elapsed time from the start of the generation process. An audio playback means that enables music selection based on voice instructions;
Music data in a navigation apparatus comprising music data storage means for storing a large number of music data, and external device connection means for connecting an external device storing the music data so that the music data can be read out to the audio playback means. A speech recognition dictionary generation program of
Generating a voice recognition dictionary for music selection from music data in the music data storage means and music data in the external device;
Measuring the degree of dictionary generation progress in units of music data storage devices in generating the voice recognition dictionary;
When a voice recognition dictionary is generated for the music data of one music data storage device and the voice recognition dictionary is generated for the music data of another music data storage device, the dictionary generation progress degree And determining a music data storage device that preferentially generates a speech recognition dictionary;
Switching the determined music data storage device so that the generation of a voice recognition dictionary of the music data is prioritized;
A speech recognition dictionary generation program for music data for causing the electronic device to execute each step.

Images