JP5431817B2 - Music database update device and music database update method - Google Patents

Description

  The present invention relates to a music database update apparatus and a music database update method, and more particularly, to a music database update apparatus and a music database update method that make up for incomplete music information and enable search based on the music information.

  In recent years, a device that stores audio information for reproduction is connected to an audio device, and music is reproduced and output based on the audio information. As such audio information, there is music data, and the music data includes tag data in which information such as the music title and artist is described together with the music digital data. It has become possible to display the title of the music being played based on the tag data on a display screen, or to read it out by voice using a TTS (Text To Speech) engine. Furthermore, it has become possible to reproduce the music by inputting the title of the music from the user.

  A user interface created based on music information added to music data is used for searching and playing music. For example, a graphical user interface is configured when operating manually, and a speech recognition dictionary is created and configured using the speech recognition dictionary when operating with speech. Information such as a music name and an artist name for each music given to such music data is added using a music information database or the like.

  However, there are cases where music information cannot be acquired from the music information database, and search and reproduction based on music information may not be possible. In such a case, in order to enable a search by album name, the album name is automatically given, for example, “My Track 0001”. Even if the music name can be automatically assigned in this way, it is unclear what kind of music is included in the automatically assigned album name.

  On the other hand, in Patent Document 1, when the album name is automatically given and the song name or artist name is changed by the user, the album name is changed according to the changed song name or artist name. The technology to do is described.

JP-A-2005-44403

  As described above, when music information cannot be acquired, the album name can be changed from the automatically given album name by the music name or artist name input by the user. As a result, the user can easily search for an album containing the desired music.

  However, in searching for music information, it is conceivable to select music by artist name or music name. In particular, music with a genre of classical music is often selected not only by music name or artist name (player name) but also by composer name such as Chopin or Beethoven. At this time, if the composer name does not exist in the acquired music information, the music cannot be searched and selected. Even if the name of the composer is included in the track name or the album name, the composer cannot be selected, and the user can select the composer based on the information of other songs. A situation occurs in which the desired music cannot be played.

  The present invention has been made in view of the problems of the prior art, and a music database updating apparatus and a music database updating method capable of searching music by automatically supplementing music information when the music information is incomplete. The purpose is to provide.

  In order to solve the above-described problems of the prior art, according to the basic form of the present invention, input means for inputting music information from an external device or medium, storage means for storing the music information, composer name or artist A personal name database storing names, and control means for storing the music information input via the input means in the storage means, the control means including the composer name in the music information of the acquired music When there is no artist name information and there is album name information, if it is determined that any person name in the person name database is included in the album name, the person name is the composer name or artist of the song. There is provided a music database update device characterized by registering a music information composer or artist as a name.

  In the music database update device according to this aspect, the control means may include any of the names in the personal name database when there is no composer name or artist name information in the acquired music information and there is track name information. When it is determined that the person name is included in the track name, the person name may be registered with the composer or artist of the song information as the composer name or artist name of the song, and voice recognition is performed. A composer / artist recognition dictionary that is referred to when the composer name or artist name does not exist in the composer / artist recognition dictionary. The control means may add the genre of the acquired music to a classic. Sometimes, it may be determined whether any person name in the person name database is included in the album name, the control means, when the genre of the acquired music is classical, It may be determined whether any person name in the person name database is included in the track name.

According to another aspect of the present invention, the step of acquiring music information from an external device or medium, the step of determining whether or not the music information of the acquired music has a composer name or an artist name, A step of determining whether or not there is an album name or a track name in the music information, and when there is no composer name or artist name in the music information, a person name is registered from a person name database in which the composer name or artist name is registered. Extracting, determining whether the extracted personal name is included in the album name or track name of the music information, and when the personal name is included in the album name or track name, Registering the person's name as a composer name or artist name of the song with the composer or artist of the song information. To update method is provided.

  In the music database update method according to this aspect, the step of determining whether or not the composer name or artist name exists in a composer / artist recognition dictionary referred to when performing speech recognition; and Adding the composer name or artist name to the composer / artist recognition dictionary when the name or artist name does not exist in the composer / artist recognition dictionary, The step of determining whether there is an album name or a track name may be performed when the genre of the music is classical.

  According to the music database update device and the music database update method of the present invention, a list of composer names or artist names prepared in advance is registered when there is no composer name or artist name information in the acquired music information. A person name is extracted from the recorded person name database, and it is determined whether or not the person name is included in the album name or track name of the music information. If the person name is included in the album name or track name, the music database is updated by registering the person name as the composer name or artist name.

  In this way, even when the composer name or artist name does not exist, the composer name or artist name having a high probability is supplemented from the album name or track name. This makes it possible to select a composer name or artist name and listen to the music. In particular, when the genre is classic, the name of the composer is often included in the album name or the track name. Therefore, even if there is no composer name in the music data, the music information can be appropriately updated. It becomes possible.

It is a block diagram which shows the structure of the information processing apparatus containing the music database update apparatus which concerns on one Embodiment of this invention. FIG. 2A is an example of the configuration of the speech recognition dictionary creation apparatus, and FIGS. 2B to 2D are diagrams for explaining creation of the speech recognition dictionary. FIG. 3A is a diagram showing an example of a music database, and FIG. 3B is an example of an interface created using the music database of FIG. It is FIG. (1) explaining the database update process in case a composer name does not exist. It is FIG. (2) explaining the database update process in case a composer name does not exist. It is FIG. (3) explaining the database update process when a composer name does not exist. It is a flowchart which shows an example of a music database update process.

  Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

  FIG. 1 is a diagram showing a configuration of an information processing apparatus 200 including a music database update apparatus 100 according to an embodiment of the present invention.

  As shown in FIG. 1, the music database update apparatus 100 according to the present embodiment includes an input unit 1a, 1b, a CDDB (CD database) 3, a control unit 4, a personal name list DB (database) 8, and a music DB. (Database) 9. The control unit 4 includes a CD information extraction unit 5, an external device music information extraction unit 6, and a music DB update unit 7.

  Furthermore, the information processing apparatus 200 including the speech recognition process includes a speech synthesis engine 10, a speech recognition dictionary generation unit 13, a speech recognition dictionary 14, a speech recognition engine 15, a speech recognition control unit 16, and a microphone 17. The music data display list generator 18, the drawing controller 19, and the display 20 are provided.

  A medium such as a CD or a DVD is connected to the input unit 1a. In addition, various devices (devices) such as a digital audio device, a USB memory, and a mobile phone are connected to the input unit 1b. Examples of the digital audio device include iPod (registered trademark: a digital music player manufactured by Apple Computer), HDD audio, and CD text. HDD audio is a portable music player with a built-in hard disk in a storage device. The CD text is a player compatible with the CD-TEXT standard, and displays text information such as a CD title and a composer.

  In the digital audio device, for example, a music file in MP3 format or the like distributed via the Internet or the like is once downloaded to a personal computer (PC), and further a music file transferred from the PC is stored. This music file includes music information (title, artist name, album name, etc.) for specifying the audio information in addition to the audio information for reproduction.

  The CDDB 3 is a music information database and stores music information such as album names, artist names, and song names of CDs (Compact Discs).

  The music DB 9 includes a hard disk, a semiconductor memory, and the like, and stores information (for example, music data in the case of a CD) stored in various devices and media input from the input units 1a and 1b.

  The control unit 4 is configured by a microcomputer, and performs the following processes in the CD information extraction unit 5, the external device music information extraction unit 6, and the music DB update unit 7, respectively.

  The CD information extraction unit 5 extracts music information from the information recorded on the input CD of the medium. For the music recorded on the CD, the information stored in the CDDB 3 is referred to extract information such as the title, artist and composer.

  The external device music information extraction unit 6 extracts music information from music stored in an external device connected to the apparatus.

  In the music DB update unit 7, the music information extracted by the CD information extraction unit 5 or the external device music information extraction unit 6 is stored in the music DB 9, and information missing from the music information is referred to the personal name list DB 8. A process for updating and updating the music DB 9 is performed.

  The speech synthesis engine 10 includes a syntax analysis unit 11 and a reading data generation unit 12. Further, the speech synthesis engine 10 is provided with a dictionary (language analysis dictionary, speech synthesis dictionary) that is used when speech synthesis is executed. The language analysis dictionary is a dictionary that is referenced when performing syntactic analysis of text information that is the target of speech synthesis processing. For each vocabulary, detailed information such as notation, reading, accent information, and part-of-speech information is supported in advance. It is the one that was added and registered. The speech synthesis dictionary is a dictionary that refers to phoneme data to be reproduced in accordance with phonetic symbols / accents obtained by the parsing unit 11.

  When the character string (text) of the information stored in the music DB 9 is input to the syntax analysis unit 11, syntax analysis such as particles and dependency is performed based on the language analysis dictionary, and the reading data generation unit 12 Generate reading data for each character string.

  The voice recognition dictionary generation unit 13 converts the reading data generated by the reading data generation unit 12 into a DB and stores it in the voice recognition dictionary 14. The voice recognition dictionary 14 includes a hard disk, a semiconductor memory, and the like, and stores a voice recognition dictionary used by the voice recognition engine 15. The speech recognition engine 15 performs acoustic analysis on the input speech to extract feature quantities, and collates the feature quantities with an acoustic model to obtain a plurality of phonetic symbol strings. A probable vocabulary is selected from the vocabulary to be recognized based on this phonetic symbol string.

  The voice recognition control unit 16 causes the voice recognition engine 15 to recognize the user's utterance voice input via the microphone 17. Based on the recognized result, information corresponding to the user's request is controlled by the drawing control unit 19 and displayed on the screen of the display 20.

  FIG. 2 is a part of the information processing apparatus of FIG. 1 and shows an example of the configuration of the speech recognition dictionary creation apparatus.

  It is assumed that the composer name in the music database in FIG. 2 is registered as shown in FIG. The composer name is input to the speech synthesis engine 10 and the syntax analysis unit 11 performs syntax analysis such as particles and dependency. The result of the syntax analysis is input to the reading data generation unit 12, and the pronunciation data of the composer name as shown in FIG. 2C is generated. As the pronunciation data of the composer name, reading data such as a phonetic symbol of each character string is generated. For example, data such as “FR AON S L IH S TD” is generated for the composer name “Franz Liszt”. Next, the speech recognition dictionary generation unit 13 creates a speech recognition dictionary using the generated composer name pronunciation data and the text stored in the corresponding music database, and composer name speech recognition dictionary. 14a.

  In FIG. 2, a voice recognition dictionary is created for the composer name in the music database, but a voice recognition dictionary is similarly generated for other information of the music information (track name, album name, artist name, etc.). And registered in each speech recognition dictionary database.

  When an external device or medium is connected to the music database update device 100 configured in this way, the music information of the music recorded on the external device or medium is extracted and the music database is updated. At this time, if there is incomplete information (for example, the name of the composer or genre is not registered) in the music information, the music database is updated by compensating for the information.

  Hereinafter, the update process of the music database related to the music data will be described taking the case of ripping the CD as an example.

  First, a music database and a user interface created based on it will be described with reference to FIG.

  FIG. 3A shows a music list created based on music information stored in the music DB 9 by connecting a CD to the input unit 1a, ripping CD data. The music information includes a track name, album name, artist name, composer name, and genre.

  In the list L1 to the list L6 in FIG. 3A, the album name is “BIG ONES”, the artist name is “AeroSmith”, the genre is “ROCK”, and the track names (song names) are “AMAZING” and “ANGEL”. , Etc. The lists L9 and L10 indicate that the genre is “Classic”, the composer name is “Beethoven”, the artist name is “Vienna Philharmonic Orchestra”, and the track name is “Symphony No. 5”. .

  A user interface is created based on the information in the music database. FIG. 3B shows an example of a user interface, and shows an interface 31 in the case of manual operation and an interface 32 in the case of voice operation.

  In the interface 31 in the case of manual operation, a menu is created and displayed on the screen of the display unit so as to correspond to each of selection by track name, selection by artist name, and the like. For example, when the user selects a music piece by the composer name, the composer is selected from the composer name selection screen. This composer name selection screen is created based on the composer list of the music database in FIG. For example, in FIG. 3B, “AeroSmith”, “Steven Tyler”, and “Ludwig van Beethoven” are displayed as composers that can be selected.

  Further, in the interface 32 in the case of voice operation, the user's utterance is recognized based on the track name, composer name, etc. registered in the voice recognition dictionary created based on the music database, and each information is selected.

  On the other hand, in the list L7 in FIG. 3A, “Piano Concerto No. 2” is registered in the music database as the track name (music name), and “Chopin Piano Concerto No. 1 & No. 2” is registered as the album name. In the list L8, “Piano Concerto No. 1” is registered in the song database as the track name (music name), and “Chopin Piano Concerto No. 1 & No. 2” is the album name in the list L8. Stored in the music database. However, as shown in the lists L7 and L8, the artist name, composer name, and genre information are missing and are not registered in the music database.

  In this case, as the operation interface, such information is not displayed on the artist name selection menu screen and the composer name selection menu screen, and the user cannot select music by these artist names or composer names.

  In the present embodiment, information that is missing from the music database in this way, in particular, when the artist name or composer name data in the case of classical music is missing, based on the album name or track name information. The missing information is compensated.

  Hereinafter, with reference to FIG. 4 to FIG. 7, processing relating to compensation for missing information will be described.

  FIG. 4 shows a process of updating the music DB 9 when the composer name does not exist. FIG. 4A is an example of music information registered in the music DB 9, and the initial state is the same as that in FIG. FIG. 4B shows a personal name list DB 8 in which a list of classic composer names is stored, which is created in advance.

  In FIG. 4A, the composer name does not exist in the original music information list L7. When this state is detected, the album name in the music information is referred to, and a word (text) is extracted from the album name. It is detected whether or not there is a word that matches the name of the classic composer list stored in the personal name list DB 8 prepared in advance. In FIG. 4A, the word “Chopin” in the album name matches the personal name “Chopin” in the personal name list DB 8. The personal name stored in the personal name list DB 8 is regarded as the composer of this album, and the music DB 9 is updated by making up for the composer name of the music information in FIG.

  Also, although the genre of this song did not exist at the beginning, it matched the name in the personal name list DB 8 of the name of the classic composer, so the genre is regarded as classic and the genre name of the music information is supplemented with “Classic”. Then, the music DB 9 is updated. Similarly, the list L8 in FIG. 4A has the composer name “Frederic Chopin / Chopin” and the genre name “Classic”. FIG. 4C shows a state after the update.

  FIG. 4D shows a composer name dictionary that is referred to when creating a speech recognition dictionary. If “Frederic Chopin / Chopin” is not registered in this composer name dictionary, this information is added.

  FIG. 5 shows an example in which, when there is no composer name and genre name among the music information created as in FIG. As shown in FIG. 5A, in the list L17 to the list L20, the album name, artist name (performer name), composer name, and genre are “Chopin: Etude work 10 / work 25” and “Maurizio Pollini”, respectively. , “Frederic Chopin” and “Classic”.

  As shown in the list L21, “Piano Concerto No. 2” is registered as the track name (music name), and “Chopin Piano Concertos No. 1 & No. 2” is registered as the album name. Similarly, as shown in the list L22, “Piano Concerto No. 1” is registered as the track name (music name), and “Chopin Piano Concertos No. 1 & No. 2” is registered as the album name. However, as shown in the list L21 and the list L22, the artist name, composer name, and genre name are not registered.

  Similarly to FIG. 4, the words of the album name are extracted, and it is detected whether or not there is a matching personal name in the personal name list DB 8 of FIG. 5B in which the extracted word is prepared in advance. In the case of FIG. 5, since the word “Chopin” extracted from the album name exists in the personal name database, this personal name is regarded as the composer name of this album, and is supplemented with the composer name of the music information. Update DB9. Also, since the name matches the name in the name list DB 8 of the name of the composer of classic music, the genre is regarded as classic, the genre name is supplemented to “Classic”, and the music DB 9 is updated. FIG. 5C shows the updated music database.

  In FIG. 5, as shown in the list L17 to the list L20, “Frederic Chopin” exists as a composer name, and since this information is registered in the composer dictionary, a new composer name is recognized. Do not register in the dictionary.

  4 and 5, the example in which the composer name and genre name are supplemented based on the album name information and the personal name list DB 8 when the composer name of the music information does not exist has been described. Then, the music information is supplemented based on the track name instead of the album name.

  As shown in FIG. 6A, the composer name information does not exist in the music information lists L31 to L35 stored in the music DB 9. Also, the album name is “Best of Best / Classic Piano”, and there is nothing that matches the name in the name list DB 8. In this case, a word of a track name (music name) is extracted, and it is detected whether or not there is a word that matches the extracted word in the personal name list DB 8.

  As shown in FIG. 6A, in the list L31, “Liszt” is included in the track name, and this word matches the word of the classic composer name in the personal name list DB 8 of FIG. 6B. . Therefore, the composer of the music in the list L31 is regarded as “Franz Liszt”, and the music DB 9 is updated by making up for the composer name of the music information.

  Similarly, for the lists L32 to L35 in FIG. 6A, refer to the classic composer name in the personal name list DB 8 in FIG. 6B for the words included in the track names, and if there is a matching personal name, The music DB 9 is updated by regarding the personal name as the composer name. FIG. 6C shows a state in which the composer name in the music database has been compensated and updated.

  If the updated composer name does not exist in the recognition dictionary that is referred to during speech recognition, the composer name is added to the recognition dictionary as shown in FIG.

  In this way, when the composer name does not exist in the album name, the composer name is estimated from the word of the track name and the composer name in the music database is supplemented.

  As described above, when the genre of a song is classic, the composer name is compensated by using the tendency that the composer of the song is often included in the album name or track name. . Therefore, although there is no guarantee that the composer name is completely compensated when the composer name does not exist, it is possible to compensate for the composer name with a high probability, and the user can select the composer's desired song. It becomes possible.

  Next, update processing of the music database when the composer name does not exist in the music information will be described with reference to the flowchart of FIG.

  First, in step S11 of FIG. 7, music information is acquired from the outside. When it is detected that an external device or medium is connected to the music database update device 100, music information is acquired and data for each item of music information is extracted.

  In the next step S12, the music database is updated based on the acquired music information. The music database is updated by adding the data for each item of each music extracted in step S11 to the music list in the music database.

  In the next step S13, it is determined whether or not the composer name exists in the music information. If the composer name exists, this process ends because it is not necessary to supplement the composer name information. If the composer name does not exist, the process proceeds to step S14.

  In the next step S14, the genre is determined based on the music information. If the genre is classic or the genre name is not described, the process proceeds to step S15. If the other genre is not classic, the process ends because it is out of the scope of this process.

  In the next step S15, it is determined whether or not an album name exists in the music information. If there is an album name, the process proceeds to step S16, and if there is no album name, the process proceeds to step S20.

  In the next step S16, it is determined whether or not the name retrieved from the classic composer list in the personal name list DB 8 is included in the album name. The classic composer list is prepared in advance and stored in the person name list DB 8. In this determination, an album name is extracted from the music information, and it is detected whether or not there is a text that matches the composer name in the classic composer list in the text of the album name.

  In the next step S17, the music database is updated. In step S16, the composer described in the album name is extracted from the classic composer list. The database is updated with the composer name as the composer name in the music information. In the update of the music database, the genre name of the music is updated to “Classic” at the same time.

  In the next step S18, it is determined whether or not the composer name exists in a recognition dictionary that is referred to during speech recognition. If the updated composer name exists in the recognition dictionary, the process ends. If the updated composer name does not exist in the recognition dictionary, the process proceeds to step S19 to add the composer name to the recognition dictionary, and the process ends.

  On the other hand, if it is determined in step S15 that there is no album name, or if it is determined in step S16 that the words included in the album name are not included in the personal name list, there is a track name in step S20. It is determined whether or not to do. If there is a track name, the process proceeds to step S21. If there is no track name, the composer name of the music cannot be estimated, and the process is terminated.

  In the next step S21, it is determined whether or not the name retrieved from the classic composer list is included in the track name. The classic composer list is the same as the list used in step S16. This determination is made based on whether or not a track name is extracted from the music information, and whether or not there is a text that matches the composer name in the classic composer list in the track name text.

  In the next step S22, the music database is updated. In step S21, the composer described in the track name is extracted from the classic composer list. The composer name is regarded as the composer name of the music information, and the music database is updated. In the update of the music database, the genre name of the music is updated to “Classic” at the same time.

  Based on the composer name recognition dictionary updated by the above music database update process, the process shown in FIG. 2 is performed to create a speech recognition dictionary.

  In the above processing, the composer name has been described, but each voice recognition dictionary is also created for other data (artist name and track name).

  As described above, according to the music database update device and the music database update method of the present embodiment, when there is no composer name or artist name information in the acquired music information, a composer name prepared in advance is provided. Alternatively, a person name is extracted from a person name database in which a list of artist names is registered, and it is determined whether or not the person name is included in the album name or track name of the music information. If the person name is included in the album name or track name, the music database is updated by registering the person name as the composer name or artist name.

  In this way, even when the composer name or artist name does not exist, the composer name or artist name having a high probability is supplemented from the album name or track name. This makes it possible to select a composer name or artist name and listen to the music. In particular, when the genre is classic, the name of the composer is often included in the album name or the track name. Therefore, even if there is no composer name in the music data, the music information can be appropriately updated. It becomes possible.

  In the above embodiment, the case where the composer name is supplemented based on the album name or the track name information of the song when the composer name does not exist as the song information has been described. When the artist name (player name) does not exist as the music information, the artist name may be supplemented based on the album name or track name information of the music. In this case, the artist name is registered in the personal name list DB 8 in advance, and when the artist name registered in the personal name list DB 8 is included in the album name or the track name, the artist name in the music information is supplemented. DB9 is updated.

100 ... Music database update device,
200: Information processing device,
1a, 1b ... input unit (input means),
3 ... CDDB,
4. Control unit (control means),
5 ... CD information extraction unit (control means),
6 ... External device music information extraction unit (control means),
7 ... Music DB update unit (control means),
8 ... Person name list database (person name database),
9 ... Music DB (storage means),
10: Speech synthesis engine,
13 ... voice recognition dictionary generator,
14: Voice recognition dictionary (composer / artist recognition dictionary).

Claims (10)

Input means for inputting music information from an external device or medium;
Storage means for storing the music information;
A name database storing composer names or artist names;
Control means for storing music information input via the input means in the storage means;
Have
The control means includes any personal name in the personal name database included in the album name when there is no composer name or artist name information in the music information of the acquired music and there is album name information. When it is determined, the music database update apparatus is characterized in that the personal name is registered with the composer or artist of the music information as the composer name or artist name of the music.   In the case where there is no composer name or artist name information in the music information of the acquired music and there is track name information, the control means includes any one of the names in the personal name database in the track name. The music database update device according to claim 1, wherein when the determination is made, the person name is registered with a composer or artist of music information as a composer name or artist name of the music.   Furthermore, a composer / artist recognition dictionary referred to when performing speech recognition is provided, and the control means, when the composer name or artist name does not exist in the composer / artist recognition dictionary, the composer name or artist The music database update device according to claim 1 or 2, wherein a name is added to the composer / artist recognition dictionary.   2. The control unit according to claim 1, wherein when the genre of the acquired music is classic, the album name is used to determine whether any personal name in the personal name database is included in the album name. The music database update device described.   3. The control unit according to claim 2, wherein when the genre of the acquired music is classic, the control unit determines whether or not any person name in the person name database is included in the track name. The music database update device described.   The music database update apparatus according to claim 3, wherein the external device is a digital audio device, and the medium is a CD or a DVD. Obtaining music information from an external device or medium;
Determining whether there is a composer name or artist name in the music information of the acquired music; and
Determining whether there is an album name or track name in the music information;
Extracting a person name from a person name database in which the composer name or artist name is registered when there is no composer name or artist name in the music information;
Determining whether the extracted person name is included in an album name or track name in the music information;
When the person name is included in the album name or the track name, the person name is registered with the composer or artist of the music information as the composer name or artist name of the music;
A music database update method characterized by comprising: Further, determining whether or not the composer name or artist name exists in a composer / artist recognition dictionary that is referred to when performing speech recognition;
Adding the composer name or artist name to the composer / artist recognition dictionary when the composer name or artist name does not exist in the composer / artist recognition dictionary;
The music database update method according to claim 7, further comprising:   The music database update method according to claim 7, wherein the step of determining whether there is an album name or a track name in the music information is performed when the genre of the music is classic.   The music database update method according to claim 7, wherein the external device is a digital audio device, and the medium is a CD or a DVD.

Images