JP7820945B2 - Information processing device, search method, and program - Google Patents

Description

The present invention relates to an information processing device, a search method, and a program.

In recent years, music distribution over the Internet has become commonplace, and various related technologies have been developed. For example, Patent Document 1 discloses a music search device that can search for desired songs using words contained in the lyrics.

Japanese Patent Application Laid-Open No. 2002-123270

When it comes to searching for music, there are a wide range of needs, such as not only simply searching for desired music, but also searching for recommendations and searching for various purposes.
SUMMARY OF THE INVENTION It is therefore an object of the present invention to provide an information processing device, a search method, and a program that are capable of searching for a desired piece of music according to the purpose of the search.

[1] An information processing device comprising: an input unit for inputting a phrase to be searched for and a query related to the lyrics of a song; and a search unit for searching a database in which songs, their lyrics, and time information related to the lyrics are stored in association with each other, and searching the database for songs whose lyrics contain the phrase to be searched for in response to the query.
[2] The information processing device according to [1], wherein the query includes at least one of information indicating the pronunciation time of the phrase and the BPM of the song.
[3] The information processing device according to [1] or [2], wherein the time information includes at least one of time information for each element of lyrics, information indicating beat or bar positions for phrases, and information indicating breath positions for phrases.
[4] An information processing device according to any one of [1] to [3], wherein the query includes information about the genre of the music, and the search unit searches for music according to the genre.
[5] An information processing device described in any of [1] to [4], wherein the phrase to be searched includes multiple parts of speech, and the search unit searches for each part of speech or for songs that include lyrics of at least some of the multiple parts of speech.
[6] The information processing device according to any one of [1] to [5], further comprising an output unit that outputs the music searched by the search unit.
[7] The information processing device according to any one of [1] to [5], further comprising a processing unit that processes the music searched by the search unit in response to a query.
[8] The information processing device described in [7], wherein the processing unit cuts out a portion of the music searched by the search unit that includes the phrase to be searched for in response to a query.
[9] An information processing device according to [7] or [8], wherein the processing unit changes the BPM of the music searched by the search unit in response to a query.
[10] The information processing device according to any one of [7] to [9], further comprising an output unit that outputs music processed by the processing unit.
[11] A search method for searching for songs from a database, the database storing songs, their lyrics, and time information related to the lyrics in association with each other, the search method including the steps of inputting a phrase to be searched for and a query related to the lyrics of the song, and searching the database for songs whose lyrics contain the phrase to be searched for in response to the query.
[12] A program for causing a computer to function as a search unit that includes an input unit for inputting a phrase to be searched for and a query related to the lyrics of a song, and that references a database in which songs, their lyrics, and time information related to the lyrics are stored in association with each other, and searches the database for songs whose lyrics contain the phrase to be searched for in response to the query.

1 is a block diagram showing a schematic functional configuration of an information processing apparatus according to an embodiment of the present invention; FIG. 10 is a diagram for explaining time information related to lyrics of a song. 3 is a flowchart illustrating a search method according to an embodiment of the present invention. 10 is a flowchart (continuation) illustrating a search method according to an embodiment of the present invention. FIG. 10 is a diagram illustrating an analysis of delimiter positions included in a query. FIG. 10 is a diagram illustrating a search when a phrase to be searched includes multiple parts of speech.

Preferred embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Note that in this specification and drawings, components that have substantially the same functional configuration will be assigned the same reference numerals, and redundant explanations will be omitted.

1 is a block diagram showing a schematic functional configuration of an information processing apparatus according to an embodiment of the present invention, which is an information processing apparatus configured by a computer.
1, information processing device 100 includes a display 110, an operation unit 120, a control unit 130, and a database 140. The functions of the above units are realized by a processor operating in accordance with a program in information processing device 100 having, for example, the hardware configuration of a computer. Information processing device 100 according to one embodiment of the present invention searches for music pieces containing a phrase desired by the user based on user operations.
The functions of each part will be further explained below.

The display 110 is a display device that displays a screen containing various types of information in the information processing device 100. As the display 110, various types of display devices such as a liquid crystal display device and an organic EL display device can be used.
The operation unit 120 includes input devices such as a keyboard and a mouse.

The control unit 130 is implemented in the information processing device 100 using, for example, a communications interface, a processor such as a CPU (Central Processing Unit), and memory that serves as a working area, and controls the operation of the information processing device 100. The control unit 130 includes an input unit 131, a search unit 132, a processing unit 133, and an output unit 134, which are realized by the processor operating in accordance with a program stored in the memory or received via the communications interface.

The input unit 131 inputs a phrase to be searched and a query related to the lyrics of the song based on a user operation via the operation unit 120 .
The phrase to be searched is a phrase indicating the lyrics desired by the user. Furthermore, a query related to song lyrics is an additional search condition related to the phrase to be searched, and includes information indicating the length of the pronunciation of the phrase (hereinafter referred to as "phrase length"), the BPM of the song, and whether the searched song needs to be processed. Note that the query may include information other than the information indicating the length of the pronunciation of the phrase and the BPM of the song. For example, the query may include information related to the genre of the song, the artist name, information about the era in which the song was produced, and topics. Topics refer to pre-categorized meta information related to songs, such as "sports,""romance,""travel,""books,""games," and "movies." Topics may also be linked to the genre of the song.

The input unit 131 inputs the following information based on a user operation via the operation unit 120.
(1) Phrase to be searched By specifying a part of the desired lyrics as text, the "phrase containing" the song to be searched for is input.
(2) Phrase Length By specifying the pronunciation time of the phrase entered in (1), the search for music containing a phrase of a certain pronunciation length is entered.
Here, pronunciation time refers to the time required to pronounce the phrase to be searched for. For example, if the phrase to be searched for is "good morning," the pronunciation time will differ depending on the song whose lyrics include "good morning." The time required to pronounce "good morning" will vary depending on various factors, such as the BPM of the song, the genre, and how the lyrics are written in the song.
Therefore, the user can input search criteria according to the purpose by specifying a phrase length, such as "pronounced in about one second." For example, the phrase length can be input depending on whether the user wants a song that pronounces "good morning" at a good tempo, or a song that pronounces "good morning" slowly and clearly.
The phrase length may be specified in seconds, beats, or bars, or in other units. At least one of an upper limit and a lower limit may be specified for the phrase length, or the phrase length may be specified within a predetermined range, such as "approximately one second." Furthermore, the phrase length may be specified by selecting one of a number of predetermined options.

Furthermore, phrase division positions may be specified in relation to phrase length. Generally, music is often divided at beat or bar positions, and by using these positions as division positions, it is possible to search for music in which the search target phrase is likely to be pronounced in a way that is comfortable for the user. Also, breath positions, where singers take breaths, are often divisions in music, and similar effects can be expected by using these positions as division positions. The division positions of such phrases should be specified by whether or not to use beat or bar positions as division positions, or whether or not to use breath positions as division positions.

(3) BPM of the song
The BPM of the input music piece may be the BPM of the original music piece, or may be the BPM of the music piece processed (adjusted) by the processing unit 133 (described later) and output from the output unit 134. For example, when the user specifies that "the BPM of the original music piece is 100 BPM," the BPM of the original music piece desired by the user is input. Also, when the user specifies that "the BPM of the processed music piece is 100 BPM, regardless of the BPM of the original music piece," the "BPM of the output music piece" desired by the user is input. Note that when specifying the BPM taking into account the processing by the processing unit 133, in order to prevent the BPM from changing significantly, it is preferable to be able to specify the difference in BPM from the original music piece, such as, for example, "the BPM of the original music piece is 90 to 110, and the BPM of the processed music piece is 100 BPM."
For example, in a DJ performance, the BPM of a song is input depending on whether or not the user desires a song that is conducive to the next song.
(4) Whether or not to Process the Music Depending on the purpose of the search, etc., whether or not to process the music by the processing unit 133 (described later) is input. Details of processing will be described later.
(5) Others As described above, the query may include information about the genre of the music, the artist name, information about the year of production, topics, etc. Such information is used as search conditions when the search unit 132 (described later) searches for music.
This information may be specified by selecting one from a number of predetermined options, or by using or recommending suitable information based on the user's personal information (ID information), such as the user's behavioral history and search history on SNS (Social Networking Service).
All or some of the requirements described in (1) to (4) may be input.

The search unit 132 searches the database 140 for songs whose lyrics contain the search target phrase in response to the query input to the input unit 131. Details of the search unit 132 will be described later.

The processing unit 133 processes the music pieces searched by the search unit 132 in accordance with the query input by the input unit 131. Here, processing of music pieces includes, for example, cutting out a portion of the searched music piece that includes the phrase to be searched for, and changing the BPM of the searched music piece. The input unit 131 receives a query indicating whether or not cutting out and BPM adjustment are required. Note that cutting out may be set to always be performed. Details of the processing by the processing unit 133 will be described later.
The output unit 134 outputs the music searched for by the search unit 132 or the music processed by the processing unit 133 .

The database 140 is configured to be able to store audio data of songs using a hard disk drive (HDD), flash memory, etc. The database 140 stores audio data of multiple songs in a predetermined format, such as MP3 format. In addition to audio information, the audio data includes tag information such as song lyrics, time information related to the lyrics, BPM of the song, artwork, title, artist name, album name, key, number of DJ plays, genre, topic, etc.
2 is a diagram for explaining time information related to the lyrics of a song. As shown in Fig. 2, the time information related to the lyrics of a song consists of lyric time data 141 indicating time information for each element of the lyrics, beat/measure position data 142 indicating the beat position or measure position of a phrase, and breath position data 143 indicating the breath position of a phrase.
For example, for the lyrics "abcdefg," playback times corresponding to the pronunciation times of each of the text "a,""b,""c,""d,""e,""f," and "g" are stored in the lyrics time data 141. Therefore, by focusing on the playback times of each text, it is possible to determine, for example, the time required to pronounce a certain phrase.
Furthermore, for a lyric portion consisting of multiple phrases such as "hij,""klm," and "nop," the lyrics time data 141 may store playback times corresponding to the pronunciation times (pronunciation times at the beginning, middle, end, etc. of each phrase) that represent each of the phrases "hij,""klm," and "nop." In this case, it is possible to more directly grasp the time required to pronounce each phrase.
Furthermore, the beat/bar position data 142 stores playback times corresponding to each beat position and bar position in the music piece, making it possible to grasp the playback times for each beat position or bar position.
The breath position data 143 also stores the playback time corresponding to each breath position in the music, making it possible to grasp the playback time of each breath position.
The time (s) in the lyric time data 141, beat/measure position data 142, and breath position data 143 are all associated with one another. Therefore, by comparing the playback times of the data, it is possible to determine the relationship between the onset time of a phrase and the beat or measure position, or the relationship between the onset time of a phrase and the breath position, etc.

The information processing device 100 may also be configured to include a communications interface, and acquire audio data stored in an external storage device, a computer, etc. via the communications interface (not shown), and store it in the database 140. In this case, the information processing device 100 does not include the database 140, and the external storage device functions as the database 140.

Next, the operation of each unit in the information processing device 100 described above when searching for a song containing a phrase desired by the user based on a user operation will be described.
3 and 4 are flowcharts showing the operation of each unit during a music search.
In the examples shown in Figures 3 and 4, first, based on user operation via the operation unit 120, a query related to the phrase to be searched and the lyrics of the song is input (step S101 YES), and the search unit 132 determines the search conditions (step S102).
The search unit 132 determines search conditions for searching the database 140 for songs based on the input phrase to be searched and a query related to the lyrics of the song.
The search unit 132 may add similar words to the input phrase to be searched for as search conditions. For example, if the phrase to be searched for is "good morning," similar expressions such as "morning" or "hi," or "ohayo" or "guten morgen" in another language, may be added as search phrases. In searching for similar words, for example, semantic vectors of phrases, which are well-known techniques, may be used to search for similar phrases. Alternatively, for example, databases of various dictionaries may be used to search for similar phrases. In either case, it is preferable that the user be able to select a desired phrase from the search results.
As described above, the BPM of the music included in the input query is the BPM of the original music, or the BPM of the music processed (adjusted) by the processing unit 133 and output from the output unit 134. Therefore, the search unit 132 determines search conditions related to BPM according to the BPM of the music included in the input query.
Furthermore, as described above, if the input query includes information about the genre of music, or if the genre or the like is specified based on the user's personal information (ID information), the search unit 132 adds such information to the search criteria. As a result, search criteria such as songs in the genre of "love songs" that include the phrase "good morning" are determined.
Furthermore, as described above, if the input query includes information about a topic, or if a topic is specified based on the user's personal information (ID information), the search unit 132 adds such information to the search criteria. As a result, search criteria such as songs related to the topic of "sports" and containing the lyrics "good" are determined.

Next, the search unit 132 searches the database 140 for songs whose lyrics include the search target phrase input to the input unit 131 in accordance with the search conditions determined in step S102 (step S103). At this time, if the above-mentioned similar words have been added to the search target phrase, the search unit 132 refers to the database for each search target phrase and searches for songs whose lyrics include the search target phrase.
Next, the search unit 132 determines whether the query input to the input unit 131 includes a specification of a delimiter position (step S104), and if it determines that a specification of a delimiter position is included (step S104 YES), the search unit 132 analyzes the specified delimiter position (step S105).
If the input query includes a specification of a delimiter position, the search unit 132 refers to the above-mentioned lyric time data 141, beat/measure position data 142, and breath position data 143 for each song searched in step S103, and analyzes the delimiter positions included in the query.
5, if the phrase to be searched is "good morning" and the breath position is specified as a break point in the query, the search unit 132 refers to the lyric time data 141 for "good morning" to find the playback time corresponding to the pronunciation time of "good morning" indicated by arrow A, and then refers to breath position data 143 to find the earliest breath position that is later than that time. The time indicated by arrow A is simply the playback time corresponding to the pronunciation time of "good morning," but the time indicated by arrow B takes into account the breath position and is a time when the user is likely to hear the phrase comfortably.
The same can be said for cases where the input query includes beat and bar position specifications as delimiter positions. In either case, the search unit 132 analyzes the delimiter positions included in the query by referencing the lyric time data 141, beat/bar position data 142, and breath position data 143, so as to extract a portion that is less likely to cause discomfort to the user in terms of content while extending before and after the phrase to be searched for, and to determine whether the beginning or end of the phrase to be searched for is the delimiter position.

Next, the search unit 132 determines whether the query input to the input unit 131 includes a phrase length specification (step S106), and if it determines that a phrase length specification is included (step S106 YES), the search unit 132 narrows down the songs according to the specified phrase length (step S107).
If the input query includes a phrase length specification, the search unit 132 narrows down the songs searched for in step S103 according to the specified phrase length. The search unit 132 refers to the lyric time data 141, beat/measure position data 142, and breath position data 143, and excludes songs that do not meet the phrase length condition included in the query, or lowers the priority in the search results of songs that do not meet the phrase length condition included in the query.
At this time, if it is determined in step S104 YES that the search result includes a specification of a delimiter position and the specified delimiter position is analyzed in step S105, the search unit 132 narrows down the search results according to the phrase length based on the analysis result. That is, rather than simply comparing the phrase length of the phrase to be searched with the phrase length specified in the query, the search unit 132 compares the phrase length of the phrase to be searched, taking the delimiter position into consideration, with the phrase length specified in the query.
By performing this process, the songs searched in step S103 can be filtered and sorted according to the query. Note that the filtering and sorting may take into account information specific to each song. For example, the filtering and sorting may take into account the popularity and recognition of the song or artist, the year in which the song was created, and so on.

Next, it is determined whether the query input to the input unit 131 includes a specification for processing the music (step S108), and if it is determined that the query includes a specification for processing the music (step S108 YES), the processing unit 133 performs processing of the music (step S109).
When processing a song, as shown in Figure 4, it is determined whether the query input to the input unit 131 includes a specification for extracting the song (step S201), and if it is determined that the query includes a specification for extracting the song (step S201 YES), the processing unit 133 performs the song extraction process (step S202).
If the input query includes a specification for processing a song, the processing unit 133 processes each song found in step S103 according to the specification.
At this time, if it is determined in step S104 that the specification of delimiter positions is included and the specified delimiter positions are analyzed in step S105, the processing unit 133 processes the music based on the analysis results. In other words, rather than simply extracting the phrases to be searched, the phrases to be searched are extracted based on the delimiter positions.
Furthermore, if the songs have been narrowed down in step S107, the processing unit 133 performs processing to cut out phrases to be searched for from each of the songs after narrowing down.
By performing such processing, it is possible to perform processing to extract phrases according to the query and extract desired phrases.

Next, it is determined whether the query input to the input unit 131 includes a specification for adjusting the BPM of the song (step S203), and if it is determined that the query includes a specification for adjusting the BPM of the song (step S203 YES), the processing unit 133 performs processing to adjust the BPM of the song (step S204).
If the input query includes a specification for adjusting the BPM of the music, the processing unit 133 adjusts the BPM of the music according to the specification for each of the music pieces found in step S103.
At this time, if the songs have been narrowed down in step S107, the processing unit 133 performs processing to adjust the BPM of each of the narrowed down songs.
By performing such processing, it is possible to perform BPM adjustment processing in response to the query and generate music with the desired BPM.

Finally, the output unit 134 outputs the music (step S110). Note that the music output to the output unit 134 differs depending on the input query in terms of whether or not the breakpoint positions have been analyzed, whether or not the music has been narrowed down by phrase length, and whether or not the music has been processed.
The output music is a lyric sample in which at least a part of a phrase of the music is extracted, and can be used for various purposes, examples of which will be described later.

The series of processes described with reference to FIGS. 3 and 4 is an example, and the present invention is not limited to this example.
For example, in the search for songs described in step S103, the search may be performed using search conditions other than the phrase to be searched, such as phrase length, etc. Also, in the narrowing down of songs described in step S105, the songs may be narrowed down using information other than information about break positions, such as the genre of the song, topic, etc.
3 and 4. For example, the analysis of breakpoint positions described in step S105 may be performed after narrowing down the songs based on phrase length described in step S107. In other words, some or all of the song search, analysis, narrowing down, and processing may be performed in any order based on the phrase to be searched and a query related to the song lyrics.

In the above example, the phrase to be searched may be composed of multiple parts of speech. In such a case, the search unit 132 searches for each part of speech or for songs containing at least some of the lyrics of multiple parts of speech independently, the processing unit 133 processes each of the searched songs, and the output unit 134 outputs songs containing each part of speech.
For example, as shown in Figure 6, if the phrase to be searched is "Dreams come true," a series of processes may be performed on the entire phrase "Dreams come true," as shown by arrow A, or a series of processes may be performed independently for each of "Dreams,""Come," and "True," as shown by arrow B, or both may be performed.
As indicated by arrow B, when a series of processes is performed for each part of speech, the phrase length may be distributed. For example, the phrase length specified for the entire phrase "Dreams come true" may be distributed to each of "Dreams,""Come," and "True," so that the sum of the phrase lengths of the three parts of speech becomes the phrase length specified for the entire phrase "Dreams come true." Furthermore, as indicated by arrow B, when a series of processes is performed for each part of speech, it is preferable to associate the output contents with each other when output by the output unit 134. Furthermore, how to divide the phrase to be searched may be determined using known analysis techniques or based on user operation.

An application example of the song search explained above will now be described.
(1) Applications in DJing, Music Production, and Video Production In applications in DJing, music production, and video production, there is a need for highly accurate music search with respect to phrase length.
For example, if there is a request to "search for songs that include the lyric phrase 'XXX' sung in two beats," then by entering "XXX" as the search phrase and "phrase length = 2 beats" as the query, songs that include the desired phrase can be accurately searched for. Also, if there is a request to "search for songs that include a sentence or phrase that is well-delimited as a word sung in one measure," then there is no need to enter a search phrase, but by entering, for example, "phrase length = 1 measure" and "delimiter position = measure position" or "delimiter position = breath position" as the query, songs that include any phrase and have the desired phrase length can be accurately searched for.
Furthermore, in music and video production applications, there is a need for highly accurate BPM searches of songs, taking into account connections with previous and subsequent songs, timing, etc. In such cases, by inputting the BPM of the original song or the processed song as a query, it is possible to accurately output phrases with the BPM the user desires.

(2) Social Service Applications In social service applications such as SNS and SMS (Social Media Service), there is a need for communication and self-expression using music. By applying the present invention to such applications, it is possible to realize, for example, a service that extracts phrases from distributed songs that have the same lyrics as input text and automatically generates the extracted lyrics as samples.
For example, if you want to "search for songs that contain lyrics that match the text entered in a messaging service and extract phrases," you can enter the "input text" as the phrase to search for, and enter a query such as "phrase length > 2 seconds,""break position = bar position," or "break position = breath position," thereby avoiding problems such as phrases that are too short to hear and allowing you to accurately search for songs that contain phrases that are musically well-defined.

(3) Applications related to dance, motion, and animation videos In applications related to dance and motion videos, similar to the applications of DJing, music production, and video production described in (1), there is a need for highly accurate song searches for phrase lengths that match the movements in dance, motion, animation, etc.
For example, when editing a video of someone dancing silently or to a certain song, adding a new or different song to that video, a user might request a search for songs that include the lyrics "XXX" and contain a phrase sung for 10 seconds. In this case, for example, by entering "XXX" as the phrase to be searched for and, for example, "phrase length = 10 seconds" as the query, and processing the results, the user's desired phrase can be accurately output.

(4) Language Learning Applications In language learning applications, there is a need to learn desired words and sentence examples using music of a specific phrase length when learning a foreign language.
For example, if you want to "search for songs that contain the lyrics 'XXX'," you can enter "XXX" as the phrase to search for, and enter, for example, "phrase length > 3 seconds" and "break position = breath position" as a query, to accurately search for songs that have a phrase length sufficient for listening practice and that contain the desired phrase, including the words before and after it, that is suitable for language learning.

(5) Sports and Exercise Applications In sports and exercise applications, there is a need to search for music with a specific phrase length and tempo for purposes such as repetitive practice and movement timing practice.
For example, when practicing the timing of movements such as "hop, step, jump," a user may want to search for songs that include the lyrics "XXX" and a phrase sung in 10 seconds. In this case, for example, by entering "XXX" as the phrase to be searched for and, for example, entering "phrase length = 8 beats" and "BPM = YY" as the query, a song containing the desired phrase can be accurately searched for.
The application examples described in (1) to (5) are merely examples, and the present invention is not limited to these examples. Furthermore, a configuration may be adopted in which some of the elements described in (1) to (5) are combined for execution.

According to one embodiment of the present invention as described above, a search phrase and a query related to the lyrics of a song are input, a database is referenced in which songs, their lyrics, and time information related to the lyrics are stored in association with each other, and songs whose lyrics contain the search phrase according to the query are searched for in the database. This allows you to search for the desired song depending on the purpose of your search.

Furthermore, according to one embodiment of the present invention, the query includes at least one of information indicating the pronunciation duration of the phrase and the BPM of the song. Therefore, it is possible to search for songs with phrase lengths or BPMs that suit the purpose of the search.

According to one embodiment of the present invention, the time information includes at least one of the following: time information for each lyric element, information indicating beat or bar positions for a phrase, and information indicating breath positions for a phrase. Therefore, rather than simply searching for songs containing a target phrase, a desired song can be searched for based on the content of the song, preferred break positions, etc.
According to one embodiment of the present invention, the query includes information about the genre of the music, and music is searched for according to the genre, making it easier for the user to search for the music they want.

Furthermore, according to one embodiment of the present invention, a phrase to be searched may include multiple parts of speech, and a search may be performed for each part of speech or for songs that include at least some of the lyrics for multiple parts of speech. Therefore, even if a phrase to be searched includes multiple parts of speech, a desired song can be searched for depending on the purpose of the search.
Furthermore, according to one embodiment of the present invention, the searched music is output, and therefore the music from which at least a partial phrase of the music is extracted can be used by the user according to their purpose.

Furthermore, according to one embodiment of the present invention, the searched music is processed in response to the query, so that the music can be processed more appropriately in response to the user's request.
Furthermore, according to one embodiment of the present invention, a portion of a searched song containing a searched phrase is extracted in response to a query, allowing the desired phrase to be extracted and used for various purposes as new audio data.

Furthermore, according to one embodiment of the present invention, the BPM of the searched music is changed in response to the query, so that the BPM of the music can be more appropriately adjusted in response to the user's request.
Furthermore, according to one embodiment of the present invention, the processed music is output, so that at least a partial phrase of the music is extracted and the music that has been processed as desired by the user can be used according to the user's purpose.

Note that part or all of the processing in the information processing device described in the above embodiment may be executed by a server connected to the Internet communication network or wirelessly so as to be able to communicate with the information processing device.
Furthermore, while the above embodiment has been described with reference to an example search targeting music, the present invention can also be applied to scripts that are not classified as music, such as speeches, recitations, and conversations. In such cases, a phrase to be searched and a query related to the script can be input, and a database in which scripts and time information related to the scripts are stored in association with each other can be referenced, and music containing the phrase to be searched for in the database in response to the query can be searched for. This configuration is particularly useful for the language learning applications described above.

The above describes in detail preferred embodiments of the present invention with reference to the accompanying drawings, but the present invention is not limited to such examples. It is clear that a person with ordinary skill in the technical field to which the present invention pertains can conceive of various modifications or alterations within the scope of the technical concept set forth in the claims, and it is understood that these also naturally fall within the technical scope of the present invention.

100...information processing device, 110...display, 120...operation unit, 130...control unit, 131...input unit, 132...search unit, 133...processing unit, 134...output unit, 140...database.

Claims (13)

an input unit for inputting a query related to lyrics of a song, the query including a phrase to be searched for and information indicating the pronunciation duration of the phrase to be searched for ;
and a search unit that references a database in which music pieces, lyrics of the music pieces, and time information related to the lyrics are stored in association with each other, and searches the database for music pieces whose lyrics include the search target phrase in response to the query. 2. The information processing device of claim 1, wherein the time information includes at least one of information indicating the playback time for each character of the lyrics or information indicating the playback time for each phrase of the lyrics , information indicating the beat position or bar position for the phrase of the lyrics, and information indicating the breath position for the phrase of the lyrics. an input unit for inputting a query related to lyrics of a song, the query including a phrase to be searched for and information indicating the pronunciation duration of the phrase to be searched for , and a delimiter position selected from beat positions, bar positions, and breath positions ;
a search unit that refers to a database in which music pieces, lyrics of the music pieces, and time information related to the lyrics are stored in association with each other, and searches the database for music pieces whose lyrics include the search target phrase in response to the query ;
Equipped with
The time information is
information indicating a playback time for each character of the lyrics or information indicating a playback time for each phrase of the lyrics;
information indicating the delimiter positions in the music piece,
The search unit narrows down the songs whose lyrics contain the search target phrase searched in response to the query to songs in which the delimiter position input by the input unit is located at the beginning or end of the search target phrase . The information processing device according to claim 1 , wherein the query includes a BPM of the song. the query includes information about the genre of the song;
The information processing device according to claim 1 , wherein the search unit searches for the music according to the genre. the phrase to be searched includes multiple parts of speech,
The information processing device according to claim 1 , wherein the search unit searches for the song containing lyrics for each of the parts of speech or at least a part of the lyrics for the plurality of parts of speech. The information processing device according to claim 1 , further comprising an output unit that outputs the music pieces searched for by the search unit. The information processing device according to claim 1 , further comprising a processing unit that processes the music searched for by the search unit in response to the query. The information processing device according to claim 8 , wherein the processing unit cuts out a portion of the music piece searched for by the search unit, the portion including the phrase to be searched for, in response to the query. The information processing device according to claim 8 , wherein the processing unit changes the BPM of the music searched for by the search unit in response to the query. The information processing device according to claim 8 , further comprising an output unit that outputs the music piece processed by the processing unit. A search method executed by a computer for searching for a song from a database, comprising:
inputting a query related to lyrics of a song, the query including a phrase to be searched for and information indicating the pronunciation duration of the phrase to be searched for ;
and searching the database, in which songs, lyrics of the songs, and time information related to the lyrics are stored in association with each other, for songs whose lyrics include the search target phrase in response to the query. an input unit for inputting a query related to lyrics of a song, the query including a phrase to be searched for and information indicating the pronunciation duration of the phrase to be searched for ;
This program causes a computer to function as a search unit that references a database in which music pieces, their lyrics, and time information related to the lyrics are stored in association with each other, and searches the database for music pieces whose lyrics contain the search target phrase in response to the query.