JP3873953B2 - Playback apparatus and program - Google Patents

Description

  The present invention relates to a playback apparatus or the like that can play back data selected from a plurality of stored content data and that can be specified by voice input when specifying a playback target.

  2. Description of the Related Art In recent years, there has been a device that extracts music data from a music CD, stores it on a hard disk together with album information such as a title and singer name (so-called ripping), and reproduces music data designated by the user from the stored music data. Has attracted attention. In particular, in the car navigation field, a navigation system equipped with a hard disk has appeared as so-called HDD navigation. If music data is stored in this hard disk, it is not necessary to set a music CD one by one. Good and convenient.

  However, since the number of songs that can be stored (the number of song albums) increases as the storage capacity of the hard disk increases, the user desires from such a lot of song data (for example, hundreds to thousands of song data). Searching and specifying music data is a heavy burden on the user.

Therefore, in order to reduce such a burden, as described in Patent Document 1, a technique of easily specifying a song title by voice input has been considered. This means that the desired music can be called directly by simply speaking the title of the music to be played.
http://www.hdd-cybernavi.com/hdd/kinou/music/index.html (see Music Server column)

  However, in the prior art, the artist name cannot be specified. In addition, regarding the album name and the song name, when speaking without specifying anything, it is limited to the recognition of the song name in the album currently being played. In other words, it is a premise that a song album is specified, and it is a small vocabulary voice recognition of the name of the song in that album, so in order to specify the playback of other songs, first recognize the album name change Speaking a command, then talking about a specific album name, and specifying a song title, it takes a considerable amount of time.

  For this reason, only the designation of another song constituting the same song album can be easily realized, but a song corresponding to another artist or another album cannot be designated freely and easily. If you dare to do it, it would take time and effort.

  The present invention has been made in view of such a problem, and an object of the present invention is to provide a playback apparatus that can specify content data such as ripped music data freely and easily by voice input.

  According to the playback device of the present invention, the storage unit stores a plurality of content data and the index data of the content data in association with each other, and the playback unit is designated among the stored content data. Content data can be reproduced. The voice recognition means inputs voice and divides the inputted voice into words for recognition. Then, the control means selects a search word used for the search from the words recognized by the voice recognition means, searches the index data stored in the storage means based on the search word, and searches for the matching data. The reproduction means reproduces the content data corresponding to the index data.

Here, the index data has name information corresponding to the content including at least the artist name and the content name corresponding to the content data, and the control means of the present invention selects the selection prepared for each content corresponding name information. The screen can be switched and displayed on the display means, and a data search is performed using a recognition dictionary prepared for each content-corresponding name information. Based on the type of the selection screen displayed on the means, the corresponding content name information is determined based on the search result.

  There are various types of content data. For example, it may be music data, image data, a pair of data, or text data. For example, in the case of music data, it corresponds to a case where music data is read from a so-called music CD and stored in a hard disk or the like as storage means. When the music data is content data, the content-corresponding name information may include at least the artist name, the music name as the content name, and the name of the music album in which the music data is a component.

  In the case of the playback apparatus of the present invention, data search is performed using a recognition dictionary prepared for each content-corresponding name information. For example, as described above, the content-corresponding name information includes an artist name, a song name, and a song album name. In other words, since each of the three name information is searched, it is possible to search from any category. That is, it is not only possible to select from the constituent songs of the currently selected album as in the prior art, but the music data stored in the storage means can be freely and easily designated by voice input. In addition, the artist name and the song album name can be specified, and the song data can be freely and easily input by voice input by selecting a song according to a predetermined rule based on the designated artist name and song album name. You will be able to choose.

  Such a simple designation by voice input is particularly effective when the playback device is mounted on a vehicle, for example. In other words, considering that the driver of the vehicle inputs via the input means, if voice input is possible instead of input by manual operation, the driver does not release his / her hand from the driving device such as the steering wheel. This is because an instruction can be given to the playback apparatus and safety is increased, so that the utility value is high.

By the way, for example, as described above, if the content-corresponding name information includes an artist name, a song name, and a song album name, it is possible that all three names are the same, or two of them are exactly the same. It is done. It is not uncommon for the artist name and the song album name to be the same, and it is not uncommon to adopt the name of a specific song constituting the song album as the album name. In that case, there arises a situation in which it is not known whether the name inputted by voice is an artist name, a song title, or a song album name.
Oite such situation reproducing apparatus of the present invention can cope. That is, the control unit can switch and display the selection screen prepared for each piece of content-corresponding name information on the display unit. If a plurality of pieces of content-corresponding name information are found as a result of the data search, the control unit displays the selection screen. It is uniquely determined based on the type of selection screen that is selected.

  For example, if there is a song “S • EED” in an album “S • EED” with an artist name “S • EED”, even if the user specifies “S • EED” by voice input, As a result, all three pieces of content-corresponding name information are hit and cannot be determined uniquely. Therefore, for example, when an artist list (list) or the like is displayed on the artist selection screen, the artist name S • EED is given priority as a search result.

  If the corresponding content-corresponding name information is a song name, the music data corresponding to the song name is played back. If the matching content-corresponding name information is a song album name, the song corresponding to the first song of the song album If the corresponding name information corresponding to the artist is an artist name, the song data corresponding to the first song is reproduced, although it is first registered in the storage means in the song album corresponding to the artist name. It is conceivable to perform control such as In this way, music reproduction can be realized with only simple voice input.

In addition, a computer according to claim 5 may be used to cause a computer to function as control means of the playback apparatus according to any one of claims 1 to 4 .
Such a program can be used by recording it on a computer-readable recording medium such as a magnetic disk, a magneto-optical disk, a memory card, etc., and loading and starting the computer as necessary. It can also be used by loading and starting up via a network. Accordingly, it is possible to easily improve the function.

  Embodiments to which the present invention is applied will be described below with reference to the drawings. The embodiments of the present invention are not limited to the following examples, and can take various forms as long as they belong to the technical scope of the present invention.

  FIG. 1 is a block diagram showing a schematic configuration of a navigation apparatus 20 as an example of a playback apparatus. The navigation device 20 is mounted on a vehicle, a position detector 21 for detecting the current position of the vehicle, an operation switch group 22 for inputting various instructions from the user, a hard disk 23 for storing various data, a navigation device. In order to display an external information input / output unit 24, a CD / DVD drive 25, which can input information to or output information from another device, and a map and various types of information. Display unit 26, voice output unit 27 for outputting various guide voices, microphone 28, position detector 21, operation switch group 22, hard disk 23, external information input / output unit 24, CD / Various processes are executed in accordance with inputs from the DVD drive 25 and the microphone 28, and the external information input / output unit 24, the display unit 26, and the audio output unit 2 are executed. A processing unit 29 for controlling, and a.

  The position detector 21 receives a radio wave transmitted from an artificial satellite for GPS (Global Positioning System) via a GPS antenna and is added to the vehicle and a GPS receiver 21a that detects the position, direction, speed, and the like of the vehicle. A gyroscope 21b for detecting the magnitude of the rotational motion, a distance sensor 21c for detecting the distance traveled from the longitudinal acceleration of the vehicle, and the like, and a geomagnetic sensor 21d for detecting the traveling direction from the geomagnetism are provided. Yes. Each of the sensors 21a to 21d has an error having a different property, and is configured to be used while complementing each other.

  As the operation switch group 22, a touch panel installed on the display screen and a mechanical key switch provided around the display unit 26 are used. The touch panel and the display unit 26 are laminated and integrated. There are various types of touch panels such as a pressure-sensitive method, an electromagnetic induction method, a capacitance method, or a combination of these methods. It may be used.

  The external information input / output unit 24 is connected to an antenna (not shown) and receives traffic information from a VICS center (not shown) via the antenna. The received traffic information is sent to the processing unit 29 and used when setting a guide route. In addition, it is connected to the Internet via a car phone or a mobile phone so that various information can be acquired.

  The CD / DVD drive 25 is a device for inputting various data stored in a CD-ROM or DVD-ROM (not shown). Examples of the CD-ROM or DVD-ROM to be input with the CD / DVD drive 25 include map data (road shape data, road width data, road regulation data, terrain data, mark data, intersection data). And so-called map CD or DVD storing facility data, etc., and so-called music CD storing music data.

  The music data read from this music CD can be stored in the hard disk 23. Further, in order to facilitate the user's selection when reproducing the music data, the music data can be stored in the hard disk 23 in correspondence with the index data. The index data includes artist name / album name / music name / genre data. These index data may be used if they are stored together with the music data on the music CD. If there is no such index data, for example, it is obtained via the Internet from a server that manages the index data. be able to. This point will be described later. Note that map data read from a map CD or DVD, sound data for facility guides / various guidance, and the like can also be stored in the hard disk 23.

  The display unit 26 is a color display device such as a liquid crystal display, an organic EL display, or a CRT, and any of them may be used. On the display screen of the display unit 26, a mark indicating the current location identified from the current vehicle position detected by the position detector 21 and the map data input from the CD / DVD drive 25, a guide route to the destination, and a name Additional data such as landmarks and various facility marks can be displayed in an overlapping manner. Also, facility guides can be displayed.

  The voice output unit 27 can output a guide voice or the like as a result of processing executed by the processing unit 29 based on facility guides and various guidance voice data stored in the hard disk 23. Further, it is possible to output a musical sound signal reproduced by the processing unit 29 based on the music data stored in the hard disk 23.

  The microphone 28 outputs an electric signal based on the inputted voice when the user inputs (speaks) the voice. The user can operate the navigation device 20 by inputting various sounds to the microphone 28.

  The processing unit 29 is configured around a known microcomputer including a CPU, a ROM, a RAM, an I / O, a bus line for connecting these components, and the like, and various types are performed based on programs stored in the ROM and the RAM. Execute the process. For example, display processing for calculating the current position of the vehicle as a set of coordinates and traveling directions based on each detection signal from the position detector 21 and displaying a map near the current position read from the hard disk 23 on the display unit 26, Route guidance for calculating the optimum route from the current position to the destination based on the point data stored in the hard disk 23 and the destination set in accordance with the operation of the operation switch group 22, and guiding the calculated route. Perform processing. In addition, the target music data selected in accordance with the operation of the operation switch group 22 is read from the hard disk 23 and reproduced, and the reproduced music signal is output via the audio output unit 27.

  In addition, when the index data is not stored in the music CD, the processing unit 29 uses a TOC (Table of Contents) information read from the music CD to set a predetermined server via the external information input / output unit 24 via the Internet. To get the corresponding index data. Then, the music data and the index data are stored in the hard disk 23 in association with each other.

  The processing unit 29 is configured to be able to execute voice recognition processing. Of course, the processing unit related to speech recognition and the processing unit related to navigation can be configured separately, but here, a configuration capable of executing speech recognition processing is constructed in the processing unit 29.

    In voice recognition, when various voices from a user are received as voice signals through the microphone 28, voice recognition is performed using voice recognition data, that is, a recognition dictionary, an acoustic model, and a language model, and it is recognized that the voice recognition is successful. Registered words (recognized words).

  The recognition dictionary includes artist name, song album name (hereinafter simply referred to as album), song (hereinafter simply referred to as song name), genre name, command (play, stop, cue, repeat, random, song number, etc.) ), Additional information of music, and the like. In addition, voice patterns of various people are registered in the acoustic model, and the voice model can be converted into text by comparing the input voice signal with the registered voice pattern. It should be noted that this voice pattern may be additionally registered individually in order to recognize the user's voice more accurately. The language model is grammatical information when the recognized speech signal is decomposed into words.

The schematic configuration of the navigation device 20 has been described so far, but correspondence between each part of the navigation device 20 and the terms described in the claims is shown.
The hard disk 23 corresponds to a storage unit, the processing unit 29 corresponds to a reproduction unit, a voice recognition unit, and a control unit, and the display unit 26 corresponds to a display unit.

  Next, description of navigation-related processing among the processing executed by the processing unit 29 is omitted, and processing related to ripping from a music CD to the hard disk 23 and music data stored in the hard disk 23 by sound input are reproduced. The process in the case of making it perform is demonstrated with reference to FIGS.

[Registering the recognition dictionary for ripping]
FIG. 2 is a flowchart showing processing relating to registration of a recognition dictionary at the time of ripping.
When the ripping mode (recording mode) is selected via the operation switch group 22 or the microphone 28, this processing starts, and guidance such as “insert a CD to be recorded” is given on the display unit 26, for example. When it is confirmed that the music CD has been inserted into the CD / DVD drive 25 (S110), the music data is ripped (S120). That is, music data (and index data, if present) is read from the music CD and stored in the hard disk 23.

  In the index data, the artist name / album name / song name is registered in the recognition dictionary in the processing unit 29 (S130). If unripped music remains (S140: YES), the processing of S120 and S130 is executed, and when the ripping processing corresponding to the song to be ripped is completed (S140: NO), this processing ends.

  If the index data is not stored on the music CD along with the music data, the index data is acquired from the management server via the Internet. In this case, the index data is registered in the recognition dictionary in S130. Just do it.

[Play music data by voice input]
FIG. 3 is a flowchart showing a process for reproducing music data by voice input.

  When the process starts, first, an area for storing a recognized artist name, a recognized album name, a recognized song name, and a recognized word in the memory in the processing unit 29 is initialized (S210). Then, the name is recognized based on the audio signal received through the microphone 28 (S220).

  Next, the recognized name is analyzed and a recognized word is registered (S230), and three types of determinations are performed on the recognized word. As described above, the recognition dictionary in the processing unit 29 is composed of an artist name, an album name, a song name, and the like. Therefore, the three kinds of recognition dictionaries of the artist name, the album name, and the song name are compared with the recognized words. If there is a match, the recognition words are registered as a recognized artist name, a recognized album name, and a recognized song name, respectively. That is, in S240, the recognized word and the recognized dictionary artist name are compared to determine whether there is a match, and if there is a match (S240: YES), the “recognized artist” in the memory in the processing unit 29 is determined. The recognition word is registered in the “name” (S250). In S260, the recognition word and the recognition dictionary album name are compared to determine whether there is a match. If there is a match (S260: YES), the “recognition album” in the memory in the processing unit 29 is determined. The recognition word is registered in the “name” (S270). In S280, the recognized word and the recognized dictionary song name are compared to determine whether or not there is a match. If there is a match (S280: YES), the “recognized song name” in the memory in the processing unit 29 is determined. The recognition word is registered in (S290).

  When the comparison between the three types of recognition dictionaries and the recognition word and the registration process (S240 to S290) based on the comparison result are completed as described above, the recognition artist name, the recognition album name, the recognition song name and the recognition word match number N are next. And a determination process based on the number of matches N is performed (S300). For example, if there is a song “S • EED” in an album “S • EED” with an artist name “S • EED”, if the user specifies “S • EED” by voice input, Since the recognized artist name, the recognized album name, and the recognized song name all match, the number of matches N = 3. Further, if there are two artist names, albums, and song names having the same name, the number of matches N = 2.

If the number of matches N = 0, the process of FIG. 3 is terminated without executing the processes after S310. If the number of matches N = 1, the process moves to S310, and the matched recognition category name is registered in the memory in the processing unit 29.
On the other hand, if the number of matches N = 2 or 3, the process proceeds to S320, and the recognition category name of the content currently displayed on the display unit 26 is registered in the memory. For example, when there is a song “S • EED” in the album “S • EED” with the artist name “S • EED” described above, the user designates “S • EED” by voice input. However, as a result of the data search, all three content-corresponding name information is hit and cannot be determined uniquely. Thus, for example, when an artist list (list) is displayed on the artist selection screen, the artist name S • EED is given priority as a search result.

  This point will be further described. At the time of reproduction of music data, a selection screen of three types of categories shown in FIG. 4 can be displayed based on music data (music data, index data, etc.) stored in the hard disk 23. That is, there are three screens: an artist name selection screen, an album name selection screen, and a song name selection screen.

  In these screens, the current selection is displayed in the first column R1 at the top, and the next second column R2 is used to instruct switching to the artist name, album name, and song name selection screen. Buttons are displayed, and you can switch to each selection screen by operating them. Below the third column R3, four names can be displayed at once. Then, by operating the displayed name portion, it is possible to shift to the artist name / album name selection screen of the corresponding name, or in the case of the song name selection screen, the station name can be selected. . Note that scroll buttons up and down are displayed on the left side of the third column R1, and by operating these buttons, it is possible to display a portion that is not currently displayed.

  For example, FIG. 4A is an example of an artist name selection screen. In the second column R2, the color of the button portion displayed as “ARTIST” has changed, and the artist name selection screen is currently displayed. I understand that. In the third column R3, the color of the button portion labeled “S • EED”, which is the third from the top, has changed, and it can be seen that “S • EED” is currently selected as the artist. FIG. 4B shows an example of the album name selection screen. The color of the button portion displayed as “ALBUM” has changed in the second column R2, and the album name selection screen is currently displayed. I understand that. In the third column R3, the color of the button portion labeled “S • EED”, which is the third from the top, has changed, and it can be seen that the album “S • EED” is currently selected. FIG. 4C shows an example of a song title selection screen. In the second column R2, the color of the button portion displayed as “TRACK” has changed, and the song title selection screen is currently displayed. I understand. In the third column R3, the color of the button portion labeled “S • EED”, which is the third from the top, has changed, and it can be seen that the song “S • EED” is currently selected.

  Returning to the description of FIG. 3, after the processing of S310 or S320, the process proceeds to S330, and the recognition category name is determined. If the recognized category name is an artist name, the first song of the song album corresponding to the artist name (the one registered first when there are a plurality of albums) is selected (S340). . If the recognized category name is an album name, the first song of the album is selected (S350). If the recognized category name is a song name, the song is selected (S360).

In S370, the music data corresponding to the music selected in S340 to S360 is read from the hard disk 23 and reproduction is started.
According to the navigation apparatus 20 of the present embodiment described above, when the music data recorded on the hard disk 23 is played, the playback target can be specified by voice input. The artist name, music album name, music name Since the search is performed by comparing the three kinds of recognition dictionaries and the recognition words, it is possible to search from any of these categories. That is, not only can it be selected from the constituent songs of the currently selected album, but the music data stored in the hard disk 23 can be freely and easily designated by voice input.

  In addition, if there is an artist name, album name, or song name that has the same name, it is uniquely determined only by a comparison between the above-described three kinds of recognition dictionaries of artist name, album name, and song name and the recognition word. In such a case, in this embodiment, the recognition category name of the content displayed on the display unit 26 can be uniquely determined.

Other embodiments will be described below.
(1) In the above embodiment, the case where the music is played back, that is, the case where the content data is the music data has been described. However, instead of the music, a moving image (for example, a movie or a promotion video) Rakugo etc.) and text (for example, newspaper articles, magazine articles, etc.) can be applied even when reproduced (displayed). Even in such a case, any of a plurality of category names such as a content name, an artist name (including the author name) for the content, a name corresponding to an album name, and the like should be searched by voice input. This is because there is a desire to be able to specify freely and easily.

  (2) In the above embodiment, an example realized as an in-vehicle system is shown, but the present invention is not limited to the in-vehicle system and can be applied to various systems. However, the ability to perform simple designation by voice input is particularly effective when applied to an in-vehicle system. This is because if the vehicle driver can input voice instead of manual input, the driver can give an instruction by voice without releasing his / her hand from the driving device such as the steering wheel, thereby improving safety.

It is a block diagram which shows the structure of the navigation apparatus of an Example. It is a flowchart which shows the process regarding registration of the recognition dictionary at the time of ripping. It is a flowchart which shows the process in the case of reproducing music data by audio | voice input. It is explanatory drawing of the selection screen of three types of categories.

Explanation of symbols

  DESCRIPTION OF SYMBOLS 20 ... Navigation apparatus, 21 ... Position detector, 21a ... GPS receiver, 21b ... Gyroscope, 21c ... Distance sensor, 21d ... Geomagnetic sensor, 22 ... Operation switch group, 23 ... Hard disk, 24 ... External information input / output part, 25 ... CD / DVD drive, 26 ... display unit, 27 ... audio output unit, 28 ... microphone, 29 ... processing unit.

Claims (6)

Storage means for storing a plurality of content data and index data of the content data in association with each other;
Reproduction means for reproducing the specified content data among the plurality of content data stored in the storage means;
Speech recognition means for inputting speech and recognizing the input speech by dividing it into words;
The search word used for the search is selected from the words recognized by the voice recognition means, and the matching data is searched from the index data stored in the storage means based on the search word, and the matched index Control means for causing the reproduction means to reproduce content data corresponding to the data;
A playback device comprising:
The index data includes name information corresponding to content including at least an artist name corresponding to the content data and a content name,
A display means for displaying various information;
Wherein, the content is the corresponding name selection screen that has been prepared for each information switchable displayed on the display unit, performs the data search using the prepared recognition dictionary for each of the content corresponding name information, the As a result of the data search, when a plurality of pieces of content-corresponding name information are applicable, suitable content-corresponding name information is uniquely determined based on the type of selection screen displayed on the display means. Playback device. The playback device according to claim 1,
The case where the plurality of content-corresponding name information is applicable is a case where a plurality of content-corresponding name information is obtained as the search result by giving the same name while being different content-corresponding name information. A reproducing apparatus characterized by that. In the reproducing | regenerating apparatus in any one of Claim 1 or 2 ,
The content data is music data,
The content-corresponding name information includes at least an artist name, a song name as a content name, and a song album name including the song data as a constituent element . The playback device according to claim 3 , wherein
The control means includes
If the compatible content-corresponding name information is a song name, the song data corresponding to the song name is played back,
If the compatible content-corresponding name information is a song album name, the song data corresponding to the first song of the song album is played back,
If the compatible content-corresponding name information is an artist name, the music data corresponding to the first song is reproduced, although it is first registered in the storage means in the music album corresponding to the artist name. A playback device. The program which makes a computer function as a control means of the reproducing | regenerating apparatus in any one of Claims 1-4. The playback apparatus according to any one of claims 1 to 4, wherein the playback apparatus is mounted on a vehicle and used.