JP5772054B2 - Singing evaluation device - Google Patents

Description

  The present invention relates to a song evaluation apparatus.

  Some karaoke apparatuses have a function of scoring the skill of singing by a singer. For example, Patent Document 1 discloses a method for calculating a score related to a pitch using a weight coefficient map. Patent Document 2 discloses a method for calculating a score related to a pitch according to a difference between reference data and pitch data in actual singing.

JP 2004-184506 A JP 2009-092771 A

In the techniques described in Patent Document 1 and Patent Document 2, the criteria for scoring the skill of singing are always the same. For example, even if there is a request for different criteria for scoring singing skills due to differences in the characteristics of the singing method depending on the genre of music, or differences in the characteristics of the singing method for each singer, Patent Document 1 and Patent According to the technique described in Document 2, since the skill of singing is always evaluated by a single criterion, the singer may not be satisfied with the scoring result.
The present invention has been made in view of the above-mentioned background, and the degree of divergence when singing is evaluated based on the degree of divergence from a predetermined criterion for a song to be sung, respectively. The purpose is to be able to change in units of singing.

In order to solve the above-described problems, the present invention is a voice data acquisition means for acquiring voice data representing a voice when a singer sings a song, and whether pitch, sound length, vibrato is good, whether or not there is inflection, When evaluating the singing of the singer according to the degree of divergence, which is the degree of divergence from a predetermined criterion for the song to be sung with respect to any one of fist presence, voice quality, and breathing, among a plurality of parameters representing the discrepancy, a parameter acquisition means for obtaining two or more parameters, using two or more parameters the acquired, the evaluation results for the singing voice of the represented acquired voice data There is provided a singing evaluation device comprising a calculating means for calculating.

Moreover, in another preferable aspect, an operation unit that receives an operation of selecting two or more parameters from the plurality of parameters is provided, and the parameter acquisition unit includes the two or more parameters selected by the received operation. To get.

  In another preferred embodiment, the plurality of parameters are determined for each song sung, a plurality of parameters determined for each genre to which the song belongs, or determined for each specific singer. At least one of the plurality of parameters is included.

Moreover, in another preferable aspect, it comprises an operation means for receiving an operation of selecting two or more parameters among the plurality of parameters, and the plurality of parameters includes a plurality of parameters determined for each song to be sung, includes a plurality of parameters other than the parameters determined for each the song, the parameter acquisition unit, when an operation of selecting the two or more parameters is accepted, the two or more parameters selected by the operation When the operation for selecting the two or more parameters is not accepted, the parameter determined for the song to be sung is acquired from the plurality of parameters determined for each song.

  In addition, the present invention provides a computer with a voice data acquisition function for acquiring voice data representing a voice when a singer sings, and a degree of deviation from a predetermined criterion for a song to be sung. A parameter acquisition function for acquiring at least any one parameter among a plurality of parameters representing the degree of divergence when evaluating the song of the singer according to the degree of divergence, and the acquired parameter as a reference Thus, the program may be provided as a program for realizing a calculation function for calculating an evaluation result for a singing by voice represented by the acquired voice data.

  According to the present invention, the parameter representing the degree of divergence when the singing of the singer is evaluated according to the degree of divergence that is the degree of divergence from a predetermined reference with respect to the song to be sung. Can be changed.

System configuration diagram of an embodiment of the present invention Block diagram showing hardware configuration of karaoke equipment Schematic diagram showing the contents of the accompaniment data storage area Schematic diagram showing the contents of the parameter data storage area Schematic diagram explaining a specific example of scoring process Flow chart when scoring is performed Schematic diagram showing the manual parameter table Schematic diagram showing parameter table by region and parameter table by time zone Schematic diagram showing the karaoke device information table 211 Diagram for explaining the formula for calculating the evaluation value of vibrato

Hereinafter, an embodiment of the present invention will be described.
<Embodiment>
<Configuration>
FIG. 1 is a diagram showing the configuration of a system according to an embodiment of the present invention.
This system includes a karaoke device 100, a server device 200, and a network NW. The karaoke device 100 is a device that reproduces karaoke music according to a request from the user and evaluates the singing by the user about the karaoke music to be played. The network NW is a LAN (Local Area Network) or the Internet, and is a communication network in which data communication is performed between the karaoke apparatus 100 and the server apparatus 200. The server device 200 serves as a reference when the content data relating to karaoke music and the karaoke device 100 evaluate the singing by the user, that is, the singing, in storage means such as an HDD (Hard Disk Drive) provided inside or outside the server device 200. The device stores parameter data and the like, and supplies the content data and parameter data to the karaoke device 100 via the network NW in accordance with a request from the karaoke device 100. Here, the content refers to a combination of audio and video related to karaoke music. That is, the content data is composed of so-called accompaniment data composed of accompaniment and chorus without the main melodic singing voice, and video data composed of the lyrics displayed on the background of the music and the lyrics. Note that a plurality of karaoke apparatuses 100 may exist for the server apparatus 200. Further, a plurality of server devices 200 may exist for the karaoke device 100.

FIG. 2 is a block diagram showing the hardware configuration of the karaoke apparatus 100.
The karaoke apparatus 100 includes a control unit 10, a storage unit 20, an operation unit 30, a display unit 40, a communication control unit 50, an audio processing unit 60, a microphone 61, and a speaker 62, and these units are connected via a bus 70. Has been. The control unit 10 includes a CPU (Central Processing Unit), a RAM (Random Access Memory), a ROM (Read Only Memory), and the like. In the control unit 10, the CPU controls each unit of the karaoke apparatus 100 by reading out a computer program stored in the ROM or the storage unit 20, loading it into the RAM, and executing it. Moreover, the control part 10 evaluates with respect to the song by a user by scoring according to the parameter data selected among the parameter data supplied from the server apparatus 200. FIG.

  The operation unit 30 includes various operators and outputs an operation signal representing the content of an operation performed by the user to the control unit 10. The display unit 40 includes, for example, a liquid crystal panel, and displays lyrics telops, background images, and the like corresponding to each karaoke piece under the control of the control unit 10. The communication control unit 50 connects the karaoke device 100 and the network NW by wire or wirelessly, and controls data communication between the karaoke device 100 and the server device 200 via the network NW.

  The server device 200 is a computer including a CPU and various memories (not shown), and particularly includes a network storage 210. The network storage 210 is, for example, an HDD, and stores content data, parameter data, and the like of karaoke music. In FIG. 2, the server device 200 includes one network storage 210, but the number of network storages is not limited to this, and the server device 200 may include a plurality of network storages. When content data of a karaoke song reserved by the user is stored in the network storage 210, the karaoke device 100 communicates with the server device 200 according to control by the communication control unit 50, and content read from the network storage 210 While downloading data via the network NW, streaming playback is performed in which playback is performed sequentially from the part where the download is completed.

  The microphone 61 outputs an analog audio signal representing the collected audio to the audio processing unit 60. The audio processing unit 60 includes an A / D (Analog / Digital) converter, converts the analog audio signal output from the microphone 61 into digital audio data, and outputs the digital audio data to the control unit 10. get. In this way, the control unit 10 functions as a voice acquisition unit that acquires voice data representing a voice when a user (singer) sings. The audio processing unit 60 includes a D / A (Digital / Analog) converter, converts digital audio data received from the control unit 10 into an analog audio signal, and outputs the analog audio signal to the speaker 62. The speaker 62 emits a sound based on the analog audio signal received from the audio processing unit 60. The storage unit 20 is a storage unit for storing various data, and is, for example, an HDD or a nonvolatile memory. The storage unit 20 includes a plurality of storage areas such as an accompaniment data storage area 21, a video data storage area 22, a GM (Guide Melody) data storage area 23, a user singing voice data storage area 24, and a parameter storage area 25.

FIG. 3 is a schematic diagram showing the contents of the accompaniment data storage area 21.
The accompaniment data storage area 21 stores information related to accompaniment data representing accompaniment sound in each music piece. The accompaniment data storage area 21 stores a plurality of accompaniment data records including a plurality of items such as “song number”, “song name”, “singer name”, “genre”, and “file storage location”. “Song number” is a number for uniquely identifying a music piece, and is composed of, for example, a 4-digit parent number and a 2-digit branch number. “Song name” represents the name of each music piece. “Singer name” represents the name of each singer. “Genre” represents the genre of music to which each musical piece belongs among a plurality of genres classified according to a predetermined classification standard. The “file storage location” represents the storage location of the data file that is the accompaniment data itself of each musical piece. When a folder called server1 or server2 is included, the data file of the accompaniment data is stored in the server device 200. When the server2 folder is not included, it means that the accompaniment data file is stored in the karaoke apparatus 100. For example, in FIG. 3, a song whose song name is “BBB” indicates that a data file of accompaniment data is stored in the server device 200, and a song whose song name is “CCC” has a data file of accompaniment data as karaoke. It is stored in the storage unit 20 of the device 100. The accompaniment data file is, for example, a MIDI (Musical Instrument Digital Interface) format file.

  The video data storage area 22 stores lyrics data indicating the lyrics of each song and background video data representing a background video displayed on the background of the lyrics. The lyrics shown by the lyrics data are displayed on the display unit 40 as lyrics telop as the music progresses during karaoke singing. In addition, the background video represented by the background video data is displayed on the display unit 40 as the background of the lyrics telop as the music progresses during karaoke singing. The GM data storage area 23 stores data indicating the melody of the vocal part of the music, that is, guide melody data (hereinafter referred to as GM data) that is data specifying the content of the constituent sound to be sung. The GM data serves as a reference for comparison when the control unit 10 evaluates the skill of singing by the user. The GM data is described in the MIDI format, for example. In the user singing voice data storage area 24, the user's singing voice collected by the microphone 61 during the period in which the accompaniment data is being reproduced for each piece of karaoke music is converted into digital data by the voice processing unit 60. Audio data generated by the conversion is stored. This voice data is called user singing voice data. This user singing voice data is stored as a data file in a WAVE (RIFF waveform Audio Format) format, for example. The user singing voice data for each song is associated with the GM data of the song by the control unit 10.

  The parameter storage area 25 stores a plurality of types of parameter data described above. These parameter data are acquired in advance by the karaoke apparatus 100 from the server apparatus 200 through the network NW. The karaoke apparatus 100 uses the parameter data stored in the parameter storage area 25 in its own apparatus for the parameter data once downloaded. When the parameter data designated by the user is not stored in the parameter storage area 25, the karaoke apparatus 100 acquires the parameter data from the server apparatus 200 as described above. There are three types of parameter data: song-specific, singer-specific, and genre-specific, and each parameter data includes an evaluation criterion used for scoring at least one or more evaluation items. The user selects an evaluation criterion used for scoring when singing along with the karaoke music piece by specifying arbitrary parameter data from the parameter data group stored in the parameter storage area 25 via the operation unit 30. Is possible. That is, the operation unit 30 functions as an operation unit that receives an operation for selecting at least one of parameters from among a plurality of parameters. In the karaoke apparatus 100, a deduction method is adopted as a scoring method. Here, the deduction method starts from a full score when a user starts singing a certain karaoke piece (100 points if the score is 100), and the control unit 10 at any time when the singing by the user does not satisfy the evaluation criteria. This is a method in which a deduction is performed by.

  FIG. 4 is a schematic diagram showing the contents of the parameter storage area 25. The parameter storage area 25 includes a song-specific parameter table 25a, a singer-specific parameter table 25b, and a genre-specific parameter table 25c. In the song parameter table 25a, a plurality of song parameter records including a plurality of items such as “song number”, “song name”, and “pitch” are described. The “song number” and “song name” are as described above. “Pitch” is an evaluation item when the control unit 10 performs scoring. When the GM data of the selected music piece is used as a reference for comparison and each note is used as a unit, a pitch deviation in the vertical direction is calculated. It shows how much is allowed. Specifically, for example, the karaoke song of the song name “AAA” in FIG. 4A allows a deviation of “100 cents (semitone)” with respect to the pitch, and the pitch between the user's singing and the pitch in the GM data If the deviation exceeds the reference value “100 cents”, it means that a deduction is performed by the control unit 10. For example, when a user sings a karaoke song having a song name “AAA”, if a note in the GM data has a pitch of “C3”, the pitch of the user's song for this note is “C3 #”. To “C3 ♭”, the control unit 10 deducts points for this note. In this way, the control unit 10 scores the singing by the user from the start to the end by the deduction method, and displays the scoring result on the display unit 40.

  In the singer-specific parameter table 25b, a plurality of singer-specific parameter records including a plurality of items such as “singer name” and “pitch” are described. The “singer name” is as described above. “Pitch” is an evaluation item when the control unit 10 performs scoring. When a singer of a specific “singer name” is selected as an evaluation standard used for scoring, the GM data of the selected music is compared. This represents how much pitch deviation is allowed in the vertical direction with each note as a unit. In the genre parameter table 25c, a plurality of genre parameter records including a plurality of items such as “genre” and “pitch” are described. The “genre” is as described above. “Pitch” is an evaluation item when the control unit 10 performs scoring. When a genre indicated by “genre” is selected as an evaluation standard used for scoring, the GM data of the selected music is compared. The reference indicates how much pitch deviation is allowed in the vertical direction with each note as a unit.

  When the user does not designate any parameter data via the operation unit 30, the control unit 10 scores the user's singing using the parameter data for each song corresponding to the reserved song title as an evaluation criterion. On the other hand, when the user designates any of the parameter data via the operation unit 30, the control unit 10 scores the user's song using the designated parameter data as an evaluation criterion. For example, consider a case where the user reserves a song indicated by the song name “DDD” in FIG. 4 and designates the singer name “The • Δ” as an evaluation criterion used for scoring. In this case, since the singer name “The ○” is designated by the user as the evaluation criterion, the pitch deviation up to “150 cents” is not subject to deduction by the control unit 10. On the other hand, in the case where the singer name “The XX” is not designated as an evaluation criterion, the control unit 10 scores the user's singing using the parameter data for each song as the evaluation criterion. Therefore, as shown in FIG. Only the pitch deviation of "" is allowed.

<Operation>
Next, the concept of scoring by the control unit 10 will be described with reference to FIG.
FIG. 5 is a schematic diagram for explaining a specific example of the scoring process. In FIG. 5, the horizontal axis represents time, and the time elapses from left to right in FIG. 5. The vertical axis represents the pitch, and the pitch increases as it progresses from bottom to top in FIG. One scale on the vertical axis means a pitch of 100 cents (semitone). That is, for example, in FIG. 5, the scale located one scale above the scale located in the area information indicated by “C3” represents the pitch of “C3 #”. Further, the scale located one scale below the scale located below the area indicated by “C3” represents the pitch of “C3 ♭”. In FIG. 5, rectangular areas 401 to 403 and 405 to 407 represent the pitches of the guide melody based on the GM data. For example, in the period shown in FIG. 5, the sound of the pitch of C3 lasts only for the period of T1, the sound of the pitch of E3 lasts for the period of T2, and then the sound of the pitch of G3 is the sound of T3. If it lasts only for a period, the silent state lasts for the period of T4. Moreover, the continuous line 300 represents the pitch of the audio | voice at the time of the user's song represented by the user song voice data mentioned above, and is hereafter called the user song voice curve 300. FIG.

  The control unit 10 acquires user singing voice data stored in the user singing voice storage area 24 and GM data associated with the user singing voice data. Moreover, the control part 10 acquires at least any one parameter data among several parameter data. As described above, the GM data serves as a reference for comparison when the control unit 10 evaluates the skill of singing by the user, and is a reference determined in advance for the song to be sung. On the other hand, the parameter data represents the degree of deviation from this GM data. For example, as described above, when “100 cents” is set as the pitch in the parameter data, the pitch deviation (that is, the degree of divergence) of “100 cents” above and below is allowed on the basis of the GM data. Represents. Here, the parameter data acquired by the control unit 10 is the selected parameter data when parameter data is arbitrarily selected by the user via the operation unit 30 when karaoke music is reserved. When no data is selected, it is parameter data for each piece of music that is the subject of singing. The control unit 10 analyzes the acquired user singing voice data, compares it with GM data associated with the user singing voice data, and calculates an evaluation value for the evaluation item based on the acquired parameter data. . This evaluation item is an evaluation item in the parameter data, and here is the degree of coincidence of pitch (pitch).

  The control unit 10 uses various known methods such as frequency analysis using FFT (Fast Fourier Transform), volume analysis, and the like as a method for analyzing the user singing voice, and calculates an evaluation value for the evaluation item, that is, an evaluation result. To do. For example, for the pitch matching degree, the control unit 10 compares the change in the pitch of the voice indicated by the user singing voice data with the change in the pitch of the guide melody indicated by the GM data, and indicates the degree of the match. An evaluation value is calculated. The evaluation value is 100% (that is, there is no deduction) if the difference between the pitches of both notes falls within the allowable range based on the parameter data, and the difference between the two pitches does not fall within the above range. If the period of the non-existing portion is half of the note length in this note in the GM data, it is 50%. That is, in a certain note, a period in which the difference between both pitches is within the above range is set as an evaluation value in GM data, which is ordered by the note length in this note. The control unit 10 determines a point to be deducted based on the calculated evaluation value. For example, when “2 points” is assigned to a certain note and the evaluation value is calculated as 50%, the control unit 10 determines “1 point” as a deduction point.

  For example, in FIG. 5, it is assumed that the user reserves a song with the song name “AAA” via the operation unit 30 and selects the genre “Rock” as a reference for evaluation used for scoring. At this time, as shown in FIG. 4, although the pitch deviation of “100 cents” is allowed in the song-specific parameter data of the song name “AAA”, “lock” is designated as the genre-specific parameter data by the user. As shown in FIG. 4, the control unit 10 allows a pitch shift of “200 cents” when scoring. If the control part 10 scores a user's song under said setting, it will become the following results. First, during the period of T1, the pitch difference of 100 cents is generated between the guide melody 401 and the end point of the user singing voice curve 300, but the evaluation reference value is a pitch deviation of “200 cents”. This is not subject to deduction by the control unit 10. Next, in the period of T2, a deviation of the pitch of 200 cents from the guide melody 402 occurs at the start of the user singing voice curve 300, but the control unit 10 allows a deviation of the pitch of "200 cents". No deduction is performed during the period T2. Next, in the period of T3, the pitch of the guide melody 403 and the pitch of 100 cents is generated at the start of the user singing voice curve 300. Here, the pitch of “200 cents” which is the reference value of the evaluation is also obtained. Therefore, no deduction by the control unit 10 is performed.

  Then, after the silent period of T4, in the period of T5, the user singing voice curve 300 maintains the same pitch as the guide melody 405, so no deduction is performed by the control unit 10. Next, in the period of T6, the guide melody 406 and the pitch shift of 400 cents have arisen in the beginning of the user singing voice curve 300. FIG. Here, since the pitch deviation of 400 cents generated in the period of T6 exceeds the allowable range of the pitch deviation of “200 cents” that is the reference value of the evaluation, the control unit 10 performs as described above. After calculating the evaluation value, a point to be deducted is determined based on the evaluation value. In the period of T7, there is a pitch deviation of 200 cents from the guide melody 407 at the start of the user singing voice curve 300, but within the allowable range of the pitch deviation of "200 cents" which is the reference value for evaluation. Therefore, no deduction by the control unit 10 is performed.

  FIG. 6 is a flowchart when the scoring process is performed. When the music is reserved by the user via the operation unit 30 (step S100; Yes), the control unit 10 searches for the reserved music from the storage unit 20 (step S102). Specifically, in step S102, the control unit 10 uses the song number or song name of the selected song from each of the accompaniment data storage area 21, the video data storage area 22, and the GM data storage area 23 as a key. Data related to the music is searched, and the search result data is read into the RAM. Next, when parameter data is selected by the user via the operation unit 30 (step S104; Yes), the control unit 10 searches the parameter storage area 25 for parameter data corresponding to the selected parameter data, and performs a search. The resulting parameter data is read into the RAM (step S108). On the other hand, when the parameter data is not selected by the user via the operation unit 30 (step S104; No), the control unit 10 sets the reserved song number as a search key (step S106). Then, the control unit 10 searches the parameter data storage area 25 using the song-specific parameter data corresponding to the song number set in the search key as an evaluation criterion, and reads the parameter data of the search result into the RAM (step S108).

  After step S108, the control unit 10 reproduces karaoke music based on the accompaniment data, video data, and GM data stored in the RAM (step S110). Specifically, in step S110, the control unit 10 causes the speaker 62 to emit sound based on the accompaniment data and the GM data, and causes the display unit 40 to display a video based on the video data. And the control part 10 memorize | stores in the user song voice data storage area 24 the user song voice data by which the user's song voice picked up by the microphone 61 is converted into digital data by the voice processing part 60 ( Step S112). When the reproduction of the karaoke music is finished, the control unit 10 scores the song based on the user song voice data stored in the user song voice data storage area 24 and the parameter data stored in the RAM (step S114). . And the control part 10 displays a scoring result on the display part 40 (step S116).

  Thus, according to the present embodiment, when the song of the singer is evaluated according to the degree of divergence, which is the degree of divergence from a predetermined criterion for the song to be sung, It is possible to change a parameter representing the degree of deviation. This makes it possible for the user to perform singing using evaluation criteria tailored to the characteristics of each song, genre, and singer without being tied to a single evaluation criterion, and higher satisfaction with the scoring results. You can get a degree.

<Modification>
The above embodiment can be modified as follows. In addition, you may implement the following modifications suitably combining.

<Modification 1>
In the embodiment, the user selects any one of the plurality of evaluation criteria, and the control unit 10 causes the display unit 40 to display a scoring result based on the selected one evaluation criterion. The evaluation criteria that can be selected by the user may be plural. In this case, the control unit 10 may perform scoring based on each selected evaluation criterion, and display the scoring results side by side on the display unit 40. In this way, the user can enjoy the difference in evaluation by obtaining a plurality of evaluation results with a single singing. Here, the control unit 10 may output an average value of a plurality of evaluation results as an evaluation result. In this way, the user can obtain an evaluation result in which a plurality of evaluation criteria are reflected simultaneously in one singing, and can enjoy a way of evaluating the singing by mixing different evaluation criteria.

<Modification 2>
In the embodiment, in order to simplify the explanation, the parameter data includes only the pitch deviation as the evaluation criterion evaluation item, but the evaluation item is not limited to this. For example, as another evaluation criterion, the control unit 10 may be any content related to the singing voice, such as pronunciation timing, tone length, vibrato quality, presence of inflection, presence of fist, voice quality, breathing, etc. Even such contents can be used as evaluation items. Specifically, as in the above embodiment, the control unit 10 stores a predetermined standard for the above-mentioned sound generation timing and the like, and a lower evaluation value as the user's song deviates from the standard. A method such as calculating may be employed. If it does in this way, it will become possible for a user to get evaluation about his song from a plurality of viewpoints.

<Modification 3>
In the embodiment, the evaluation criteria that can be selected by the user via the operation unit 30 are selected from the parameter data for each song, each singer, or each genre received from the server device 200. It is not limited to this. For example, the user may be able to manually set the degree of severity of the evaluation criteria via the operation unit 30. In this case, for example, the parameter storage area 25 includes a manual parameter table. FIG. 7 is a schematic diagram showing the manual parameter table 25d. The user selects an arbitrary one from a plurality of evaluation criteria such as “easy”, “normal”, and “difficult”. Here, as shown in FIG. 7, if the evaluation criterion is related to pitch, when “easy” is selected, the allowable range of pitch deviation is the largest, and “difficult” is selected. If this is selected, the allowable range of pitch deviation will be the smallest, and if “Normal” is selected, the allowable range of pitch deviation will be between “Easy” and “Difficult”. is there. In this way, the user can change the evaluation standard step by step according to the singing ability, so even if the skill of the singing varies among multiple users, the level in the singing of the singer It is possible to enjoy the way of setting evaluation criteria according to the situation and gradually increasing the difficulty level.

  For example, the parameter storage area 25 may include a regional parameter table or a time zone parameter table. FIG. 8 is a schematic diagram showing the regional parameter table 25e and the time zone parameter table 25f. For example, in the case of the regional parameter table 25e, parameter data corresponding to pronunciation nuances for each region may be associated with each specific region (for example, Kanto, Kansai, Tohoku, etc.). For example, compared to the Kanto region, where standard words have permeated, the Kansai region has a strong persistence of its own Kansai dialect, and there is a high probability of strong intonation when speaking. Therefore, in this case, regarding the pitch, in the parameter data in which the area is “Kansai”, the allowable range of pitch deviation may be set larger than in the parameter data in which the area is “Kanto”. In this way, scoring is performed in consideration of differences in pronunciation nuances according to dialects of each region. The setting of parameter data in the above and FIG. 8 is an example. For example, “Kanto” and “Kansai” are set to “100 cents”, only “Tohoku” is set to “200 cents”, and a wide area classification (example: It is possible to set parameter data for each of “Eastern Japan” and “Western Japan”) or subdivided regions. Furthermore, it is possible to set not only the classification based on the administrative division but also the parameter data based on the original regional classification based on the dialect determined in advance according to the present invention.

  Further, in the time zone parameter table 25f in FIG. 8, the allowable range of pitch deviation is large with respect to the pitch in the time zone from night to early morning and in the time zone from morning to noon. This is based on the following idea. In the time zone from night to early morning, there is a high probability that the user is ingesting alcohol. In such a case, it is considered that the singing ability often falls compared to when the user is not ingesting alcohol. In addition, during the time period from morning to noon, it is possible that there are many users who have not woken up so much time. It is thought that it is often difficult. Therefore, when the user selects the time zone as an evaluation criterion, for example, for pitch evaluation items, it is only necessary to allow a wider pitch shift than time zones other than the time zone. As for the parameter data for each time zone, the user may automatically select the time zone for which the user has performed an operation only by selecting “by time zone” as the evaluation criterion. In this case, the control unit 10 acquires time from the timekeeping function provided in the karaoke apparatus 100, and acquires the evaluation reference value by searching the parameter table 25f for each time zone by the acquired time. The setting of the parameter data in the above and FIG. 8 is an example. For example, the pitch deviation is changed with respect to the daytime period (eg, 12: 00 to 17:00) that is considered to be a lot of students, housewives, and elderly people. It is possible to set “300 cents”, which is more widely permitted, and to set “100 cents” for other time zones. Furthermore, the setting based on the classification from the viewpoint of “weekdays” or “weekends” is not limited to the setting for the time zone in one day. In this case, the “weekend” in which the user is likely to be ingesting alcohol may be set so as to allow a wider pitch shift compared to “weekdays”. As described above, the time zone parameter can be arbitrarily set by the designer in the design.

<Modification 4>
The karaoke apparatus 100 is connected to the server apparatus 200 via the network NW, but this system configuration may be used as follows. The network storage 210 of the server device 200 includes a karaoke device information table 211 in which information related to the connected karaoke device 100 (in which region, in which store, etc.) is stored. By using the server device 200, the parameter data corresponding to the area or the store where the karaoke device 100 is installed may be distributed to the karaoke device 100.

  FIG. 9 is a schematic diagram illustrating the karaoke apparatus information table 211. “Karaoke device ID” is an identifier for uniquely identifying each karaoke device, and is represented by, for example, a seven-digit alphabet. “Region” represents an area where the karaoke apparatus 100 that holds the associated karaoke apparatus ID is installed. “Store type” represents the type of the store in which the karaoke apparatus 100 that holds the associated karaoke apparatus ID is installed. The server device 200 acquires the karaoke device ID from the karaoke device 100 connected through the NW. And the server apparatus 200 can acquire the information regarding the area | region and each shop type in which each karaoke apparatus was installed by searching the karaoke apparatus information table 211 using acquired karaoke apparatus ID. If it does in this way, compared with the case where the server apparatus 200 delivers the same parameter data uniformly with respect to all the connected karaoke apparatuses 100, the area where each karaoke apparatus 100 is installed, and every store Different parameter data can be distributed according to the characteristics. This makes it possible to distribute appropriate parameter data according to regional characteristics and store type differences (karaoke stores, snacks, etc.). Here, the regional features are as described above. As for the difference in store type, for example, if it is a snack, it is likely that the user is ingesting alcohol, so parameter data with a large allowable range of pitch deviation will be delivered compared to karaoke stores You can do it. In this way, the server device 200 transmits only necessary data, thereby reducing the amount of data to be distributed, reducing the load on the network NW, and storing data stored in the storage unit 20 of the karaoke device 100. By reducing the amount, the storage capacity of the storage unit 20 can be used effectively.

<Modification 5>
In the embodiment, when a calculation formula for calculating a point to be deducted (that is, an evaluation result) is provided, the control unit 10 changes the coefficient and threshold used in the calculation formula according to the parameter data. Also good. In this case, each parameter table stores not only a reference value such as an allowable range related to pitch, but also the above-described coefficient and threshold value itself. And the control part 10 calculates an evaluation result, using the coefficient and threshold value which are contained in the parameter data selected as evaluation criteria for the above-mentioned calculation formula.

As a specific example of the modified example 5, consider an example using a calculation formula related to vibrato, for example.
FIG. 10 is a diagram for explaining a calculation formula for calculating the evaluation value of vibrato. In FIG. 10, the horizontal axis represents time, and the time elapses from left to right in FIG. 10. The vertical axis represents the pitch, and the pitch increases as it progresses from bottom to top in FIG. A guide melody GM represented by a solid line represents the pitch of the guide melody. A user singing voice curve 500 represented by a curve represents the pitch of the voice of the user singing. The peak pitch widths p1 and p2 represented by the vertical arrows are widths in the pitch direction between the peak of the pitch in the user singing voice curve 500, and the fluctuation of the vibrato pitch in the user's singing. Represents the width. Peak time widths t1 and t2 represented by arrows in the horizontal direction are widths in the time direction between pitch peaks in the user singing voice curve 500, and represent the period of vibrato in the user singing.

Here, the dispersion of the peak pitch widths p1 to pn is Vp, the dispersion of the peak time widths t1 to tn is Vt, the pitch coefficient to be multiplied by Vp is α, the time coefficient to be multiplied by Vt is β, and the threshold is k. Sometimes, the formula for vibrato skill determination is expressed by the following equation (1). The pitch coefficient α, the time coefficient β, and the threshold value k are one of the threshold values included in the parameter data described above. The pitch coefficient α and the time coefficient β are different values depending on differences in music, singer, genre, etc., and the sum of the pitch coefficient α and the time coefficient β is 1.0.

  In Expression 1, when the value on the left side is smaller than the threshold value k on the right side, the control unit 10 determines that the vibrato skill is good. On the other hand, in Equation 1, when the value on the left side is larger than the threshold value k on the right side, the control unit 10 determines that the vibrato skill is poor. Since Vp is the dispersion of the peak pitch width, the larger the value, the greater the variation in the interval between the vibrato peaks in the pitch direction, and the smaller the value, the greater the interval between the vibrato peaks in the pitch direction. It shows that there is little variation. Further, Vt is the dispersion of the peak time width, so that the larger the value, the greater the variation in the interval between the vibrato peaks in the time direction, and the smaller the value, the interval between the vibrato peaks in the time direction. This means that there is little variation.

  For example, let us consider a case where the user selects the singer name “The △” from the singer-specific parameter data. It is assumed that the vibrato when the singer “The △△” sings has a dynamic pitch range with a large variation in the pitch direction, while a fluctuation in the time direction is relatively accurate and has a small variation. In this case, each coefficient is set so that “α <β” when the singing evaluation apparatus is designed. If it does in this way, the singing method according to the characteristic of the singer "The * △" will be more highly scored by the control unit 10.

Also, for example, in addition to vibrato, when pitch and pronunciation timing are to be scored, the pitch score is multiplied by Pitch, the score result for pitch is Vib, the score result for vibrato is Vib, and the score result for pronunciation timing is Timing. The mathematical expression for calculating the score Pt is expressed by the following equation (2), where γ is the scoring coefficient, δ is the vibrato scoring coefficient that multiplies Vib, ε is the pronunciation timing scoring coefficient that multiplies Timing, and Pt is the score. Here, the sum total of the pitch scoring coefficient γ, the vibrato scoring coefficient δ, and the pronunciation timing scoring coefficient ε is 1.0.

  For example, consider a case where the user selects the singer name “Yama * Taro” in the parameter data for each singer. It is assumed that the singer “Yama * Taro” has a relatively accurate pitch in the singing and vibrato has a large variation in the pitch direction, so it cannot be said to be a beautiful vibrato and the pronunciation timing seems to be delayed. In such a case, each coefficient is set so that “δ <ε <γ” or “ε <δ <γ” at the time of designing the singing evaluation apparatus. If it does in this way, the singing method in accordance with the characteristics of the singer “Yama ○ Taro” will be more highly scored by the control unit 10.

<Modification 6>
In the embodiment, since the storage unit 20 includes the parameter data storage area 25, the control unit 10 acquires the parameter data from the parameter data storage area 25. However, the present invention is not limited to this, and the storage unit 20 Without providing the storage area 25, the control unit 10 may receive and obtain necessary parameter data from the server device 200 at timings before and after receiving content data, for example. In this case, the control unit 10 notifies the server device of information necessary for the server device 200 to select parameter data. In this way, the storage capacity of the storage device required by the karaoke apparatus 100 can be reduced, and the same effects as in the embodiment can be achieved.

<Modification 7>
In addition to the singing evaluation apparatus, the present invention can be understood as a method for realizing these and a program for causing a computer to realize a voice evaluation function. Such a program may be provided in the form of a recording medium such as an optical disk storing the program, or may be provided in the form of being downloaded to a computer via the Internet or the like and installed and used.

  DESCRIPTION OF SYMBOLS 10 ... Control part, 20 ... Memory | storage part, 21 ... Accompaniment data storage area, 22 ... Image | video data storage area, 23 ... GM data storage area, 24 ... User song audio | voice data storage area, 25 ... Parameter storage area, 25a ... By song Parameter table, 25b ... Parameter table by singer, 25c ... Parameter table by genre, 25d ... Manual parameter table, 25e ... Parameter table by region, 25f ... Parameter table by time zone, 30 ... Operation unit, 40 ... Display unit, 50 ... Communication control unit, 60 ... Audio processing unit, 61 ... Microphone, 62 ... Speaker, 70 ... Bus, 100 ... Karaoke device, 200 ... Server device, 210 ... Network storage, 211 ... Karaoke device information table, 300, 500 ... User singing Voice curve, 401-403, 405-407 ... guy Melody, GM ... guide melody, NW ... network, p1, p2 ... peak pitch width, t1, t2 ... peak time width

Claims (4)

Voice data acquisition means for acquiring voice data representing voice when a singer sings a song;
Degree of divergence, which is the degree of divergence from a predetermined standard with respect to the song to be sung in any one of pitch, sound length, vibrato quality, presence / absence, fist presence, voice quality, and breathing Parameter evaluation means for acquiring two or more parameters among a plurality of parameters representing the degree of deviation when evaluating the song of the singer according to
A singing evaluation apparatus comprising: a calculating unit that calculates an evaluation result for a singing by voice represented by the acquired voice data using the two or more acquired parameters. An operation means for receiving an operation of selecting two or more parameters from the plurality of parameters;
The singing evaluation apparatus according to claim 1, wherein the parameter acquisition unit acquires the two or more parameters selected by the accepted operation. The plurality of parameters are any of a plurality of parameters determined for each song to be sung, a plurality of parameters determined for each genre to which the song belongs, or a plurality of parameters determined for each specific singer The singing evaluation apparatus according to claim 1 or 2, characterized by comprising: An operation means for receiving an operation of selecting two or more parameters from the plurality of parameters;
The plurality of parameters include a plurality of parameters determined for each song to be sung and a plurality of parameters other than the parameters determined for each of the songs,
The parameter acquisition unit, when an operation of selecting the two or more parameters is accepted, the operation of acquiring the two or more parameters selected by the operation, selects the two or more parameters is accepted When there is not, the parameter determined about the music used as the object of singing among a plurality of parameters determined for every music is acquired. The song evaluation apparatus according to claim 1 characterized by things.

Images