JP2007256617A - Musical piece practice device and musical piece practice system - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide technology for informing a singing person (or a playing person) of a part which is likely to be mistaken in a karaoke system. <P>SOLUTION: When a song is selected by the singing person (or the playing person), a CPU 11 of the karaoke system 2 reads an accompaniment data of an indicated song and supplies it to a sound processing section 18. The sound processing section 18 converts the supplied accompaniment data to an analog signal and sound is output by supplying the signal to a speaker 19. At this time, the CPU 11 recognizes which position of the song the accompaniment signal generated by the sound processing section 18 is located, and compares the recognized position with a starting position of period indicating information acquired from a server unit 3. When difference of the both becomes the predetermined difference, the period indicated by the period indicating information is informed. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a music practice device and a music practice system.

In a karaoke apparatus, various methods for scoring the skill of a singer's singing have been proposed. For example, Patent Document 1 proposes a method of determining which part has not been successfully sung by comparing the pitch of the sung voice with a reference pitch. Further, Patent Document 2 proposes a method of storing the singer's past scoring results and increasing the volume of the guide melody for a phrase having a poor score. In addition, a method has been proposed in which a scoring result is transmitted to a server to perform ranking (see, for example, Patent Document 3).
Japanese Patent Application Laid-Open No. 2004-093601 JP 2005-049410 A Japanese Patent Laying-Open No. 2005-099288

By the way, in the methods described in Patent Document 1 and Patent Document 2, it is impossible to grasp which part is wrong unless the singer sings once. Therefore, when a singer sings the music for the first time, the singer cannot grasp what part of the music should be sung. The same applies to musical instrument performance.
The present invention has been made under the above-described background, and an object of the present invention is to provide a technique capable of notifying a singer in advance of easily mistaken parts in a karaoke apparatus.

In order to solve the above problems, the present invention provides accompaniment data storage means for storing accompaniment data constituting accompaniment sounds of music, acquisition means for acquiring section designation information indicating a specific section of the music, and start of accompaniment And when the start of the accompaniment is instructed by the instruction means, the accompaniment data is read from the accompaniment data storage means according to the progress of the music, and an accompaniment sound signal is generated based on the read accompaniment data An accompaniment sound signal generating means, an accompaniment position recognizing means for recognizing which position of the music the accompaniment sound signal generated by the accompaniment sound signal generating means, a position recognized by the accompaniment position recognizing means and the acquisition means And a notifying means for notifying the section indicated by the section designation information when the difference between the two is a predetermined difference. To provide music training device according to claim.
In a preferred aspect of the present invention, the section designation information includes feature data indicating the characteristics of the section to be specified, and the notification means notifies the section in advance according to the feature data together with the notification of the section. It is characterized by performing.

The present invention also provides accompaniment data storage means for storing accompaniment data constituting accompaniment sounds of music, model voice data storage means for storing model voice data representing melodic sounds included in the music, and the music Acquisition means for acquiring section designation information indicating a specific section, an instruction means for instructing the start of accompaniment, and the accompaniment data storage according to the progress of the musical piece when the start of the accompaniment is instructed by the instruction means Accompaniment data is read from the means, and accompaniment sound signal generation means for generating an accompaniment sound signal based on the read accompaniment data, and the position of the music corresponding to the accompaniment sound signal generated by the accompaniment sound signal generation means is recognized Accompaniment position recognition means, the acquisition means at a timing when the position recognized by the accompaniment position recognition means coincides with the start position of the section designation information acquired by the acquisition means Voice signal generation means for reading out the model voice data corresponding to the section indicated by the section designation information acquired from the model voice data storage means and generating a voice signal based on the read model voice data. A characteristic music practice device is provided.
The present invention also provides accompaniment data storage means for storing accompaniment data constituting accompaniment sounds of music, acquisition means for acquiring section designation information indicating a specific section of the music, and sections acquired by the acquisition means Corresponding to the section indicated by the section specifying information acquired by the acquiring means when the start of accompaniment is instructed by the specific section instructing means for instructing the start of accompaniment from the section indicated by the specifying information There is provided a music practice device comprising: accompaniment sound signal generation means for reading out partial accompaniment data from the accompaniment data storage means and generating an accompaniment sound signal based on the read accompaniment data.

In a preferred aspect of the present invention, the accompaniment data includes position information indicating the position of a song, and the accompaniment position recognition means is generated by the accompaniment sound signal generation means from position information included in the accompaniment data. It is characterized by recognizing which position of the music the accompaniment sound signal is applied to.
In another preferred aspect of the present invention, the accompaniment position recognizing means is adapted to determine which accompaniment sound signal generated by the accompaniment sound signal generating means is in accordance with a process of reading accompaniment data by the accompaniment sound signal generating means. It is characterized by recognizing whether it corresponds to a position.

Further, in a further preferred aspect of the present invention, input means for accepting input of trainer data representing a trainee's voice, and model data stored in the model data storage means are input in advance. Comparing means for generating and outputting difference information indicating the degree of difference between the two comparison sections for each comparison section in comparison with each other.
Further, in a further preferred aspect of the present invention, the model data is data representing a melody pitch of music, and the music practice device includes pitch calculation means for calculating a pitch of voice from the trainee data, The comparison means compares the pitch calculated by the pitch calculation means and the pitch indicated by the model data stored in the model data storage means for each comparison section, and shows difference information indicating the degree of difference between the two. Is generated for each comparison section.
Also, in a preferred aspect of the present invention, the model data is data representing the lyrics of the music, and the music practice device recognizes the voice represented by the trainer data and recognizes the recognized voice. Voice recognition means for generating a character string, and the comparison means compares the recognized character string generated by the voice recognition means with the model data stored in the model data storage means for each comparison section. The difference information indicating the degree of difference between the two is generated for each comparison section.
Also, in a preferred aspect of the present invention, the model data is technique data indicating a type and timing of a technique used for a model song.
Further, in a preferred aspect of the present invention, the practitioner data is data representing a performance sound of an input musical instrument, and the model data is data representing a performance sound of a musical instrument used as a model. And
In addition, the present invention has a plurality of the above-described practice devices, receives the difference information generated by the comparison means of each music practice device via a network, the statistics of the received difference information for each comparison section, Comprising a server device having section specifying information generating means for generating a section specifying information for extracting a comparison section in which a statistical result satisfies a predetermined condition and indicating the extracted comparison section as a specific section of the music; The acquisition means of each music practice device provides a music practice system characterized by acquiring section designation information from the server device.

  According to the present invention, it is possible to notify a singer in advance of an easily mistaken location.

<A: First Embodiment>
<A-1: Configuration>
FIG. 1 is a block diagram showing an example of the overall configuration of a music practice system 1 according to an embodiment of the present invention. This system is configured by connecting karaoke apparatuses 2 a, 2 b, 2 c and a server apparatus 3 via a communication network 4. In addition, although three karaoke apparatuses are illustrated in FIG. 1, the number of karaoke apparatuses contained in this music practice system is not limited to three, and may be more or less than this. In the following description, when it is not necessary to distinguish the karaoke apparatuses 2a, 2b, and 2c, they are simply referred to as “karaoke apparatus 2”.

  FIG. 2 is a block diagram illustrating a hardware configuration of the karaoke apparatus 2. A CPU (Central Processing Unit) 11 reads a computer program stored in a ROM (Read Only Memory) 12 or a storage unit 14, loads it into a RAM (Random Access Memory) 13, and executes it to execute a karaoke apparatus. 2 parts are controlled. The storage unit 14 is a large-capacity storage unit such as a hard disk, and includes an accompaniment data storage area 14a, a lyrics data storage area 14b, a trainer voice data storage area 14c, a scoring result data storage area 14d, and a model voice. And a data storage area 14e. The display unit 15 is a liquid crystal display, for example, and displays various screens such as a menu screen for operating the karaoke device 2 and a karaoke screen in which lyrics telop is superimposed on a background image under the control of the CPU 11. The operation unit 16 includes various keys and outputs a signal corresponding to the pressed key to the CPU 11. The microphone 17 is a sound collecting unit that picks up the sound produced by the singer. The sound processing unit 18 converts sound (analog data) collected by the microphone 17 into digital data and supplies it to the CPU 11. The speaker 19 is connected to the sound processing unit 18 and emits sound with an intensity corresponding to a signal output from the sound processing unit 18. The communication unit 20 includes various communication devices and the like, and exchanges data with the server device 3 via the communication network 4 under the control of the CPU 11.

  The accompaniment data storage area 14a of the storage unit 14 is, for example, accompaniment data in the MIDI (Musical Instruments Digital Interface: registered trademark) format, and the melody pitch (pitch) and strength of various instruments that accompany each song ( Accompaniment data in which information indicating the (velocity) and the application of effects is written according to the progress of the music is stored. The accompaniment data includes melody data indicating the scale of the melody of the music. In this embodiment, this melody data is used as model data. The accompaniment data includes measure number information (position information) indicating the number of the measure in the song. The lyrics data storage area 14b stores lyrics data indicating lyrics corresponding to the accompaniment data.

  In the practitioner audio data storage area 14c, audio data A / D converted from the microphone 17 via the audio processing unit 18 is stored in time series, for example, in the WAVE format or MP3 (MPEG Audio Layer-3) format. Since this voice data is voice data representing the voice of the practitioner (hereinafter referred to as “practice voice”), it is hereinafter referred to as “practice voice data”.

  In the scoring result data storage area 14d, difference information indicating the degree of difference between the trainer voice data and the melody data is stored. The CPU 11 of the karaoke device 2 compares the trainer voice data and the melody data for each predetermined section (comparison section), and generates and generates difference information indicating the degree of difference between the two for each section. The difference information is stored in the scoring result data storage area 14d.

FIG. 3 is a diagram illustrating an example of the contents of scoring result data. As shown in the figure, the scoring result data is stored with the items of “section number”, “pitch score”, and “lyric score” being associated with each other. Among these items, “section number” stores information for identifying the sections constituting the music. In this embodiment, “section number” uses measure number information assigned to each measure in units of one measure. In the “pitch score” item, difference information indicating the degree of difference between the pitch of the trainer voice data and the pitch of the melody data in the section corresponding to the “section number” is stored. In the example shown in FIG. 3, the numerical value converted into the score of 100 perfect score is shown as a pitch score. In the example of FIG. 3, the larger the numerical value of the number of pitch points, the closer the pitch between the two, and the smaller the numerical value, the different the pitch between the two.
In the “Lyric score” item, difference information indicating the degree of difference between the lyrics of the practicer voice data and the lyrics data in the section corresponding to the “section number” is stored. In the example shown in FIG. 3, this “lyric score” also indicates a mode in which a numerical value converted into a score of 100 points is stored as the lyrics score, as with the above “pitch score”.

  Next, in the exemplary audio data storage area 14e of the storage unit 14, for example, audio data in WAVE format or MP3 format, which is used as an exemplary model for singing a song and represents audio of melody included in the song (Hereinafter “model voice data”) is stored.

  FIG. 4 is a block diagram illustrating a hardware configuration of the server device 3. The CPU 31 reads out a computer program stored in the ROM 32 or the storage unit 34, loads it into the RAM 33, and executes it to control each unit of the server device 3. The storage unit 34 is a large-capacity storage unit such as a hard disk, for example, and includes a scoring result database storage area 34a and a section designation information storage area 34b. The communication unit 35 includes various communication devices and the like, and exchanges data with the karaoke device 2 via the communication network 4 under the control of the CPU 31.

The scoring result database storage area 34a of the storage unit 34 stores a scoring result database that is a set of scoring result data. This scoring result database has a pitch scoring result table and a lyrics scoring result table for each music piece.
FIG. 5 is a diagram illustrating an example of the contents of the pitch scoring result table. As shown in the figure, this table stores items of “section number”, “number of pitch points”, “number of errors”, and “error rate” in association with each other. Among these items, “section number” and “pitch score” store data similar to those shown in the above-described scoring result data. However, in this table, as shown in the figure, the number of pitch points in a plurality of songs (“the number of pitch points (song A, song B...)”) Is stored in association with the “section number”. Next, a numerical value indicating the number of scoring results indicating that the degree of difference is large is stored in the item “number of errors”. For example, if the threshold is 60 (%), the “number of errors” corresponding to “section 1” is “pitch score” corresponding to “section 1”, and the value is 60 or less. The total number is stored. In the example illustrated in FIG. 5, the “section 1” illustrates a case where the number of pitch points having a large difference is 1.
Next, in the item “error rate”, a value obtained by dividing “number of errors” by the total number of songs in the number of pitch points is stored.
The contents of the lyrics scoring result table are also the same as the contents of the pitch scoring result table shown in FIG. 5, and the description thereof is omitted here.

Next, in the section specifying information storage area 34b of the storage unit 34, section specifying information indicating a specific section of music such as a section in which lyrics are likely to be mistaken or a period (pitch) is likely to be mistaken is stored.
FIG. 6 is a diagram illustrating an example of the contents of the section designation information. As shown in the figure, the section designation information is stored in association with items of “song code”, “section number”, and “feature data”. Among these items, information for identifying music is stored in the “music code” item. In the “section number” item, bar number information is stored. In the item of “feature data”, for example, information indicating the characteristics of the specified section such as “pitch error” and “lyric error” is stored.

<A-2: Operation>
Next, the operation of the music practice system 1 will be described.
<A-2-1: Scoring result statistical operation>
First, the scoring result statistical operation of the music practice system 1 will be described with reference to the flowchart shown in FIG.
The practitioner operates the operation unit 16 of the karaoke apparatus 2 to select a song to be sung. At this time, prior to reproducing the accompaniment of the song, the CPU 11 of the karaoke apparatus 2 performs a notification operation for a portion where the mistake of the song is likely to occur, but since this notification operation will be described later, the description thereof is omitted here.
The practitioner operates the operation unit 16 of the karaoke apparatus 2 to instruct the reproduction of the accompaniment data of the song to be sung. The CPU 11 starts the process shown in FIG. 7 in response to this instruction. First, the CPU 11 reads the accompaniment data of the designated song from the accompaniment data storage area 14a and supplies it to the audio processing unit 18 (step S1). The sound processing unit 18 converts the supplied accompaniment data into an analog signal and supplies it to the speaker 19 for sound emission. At this time, the CPU 11 may control the display unit 15 to display a message prompting singing such as “Please sing along with the accompaniment”. The practitioner sings along with the accompaniment emitted from the speaker 19. At this time, the voice of the practitioner is picked up by the microphone 17 and converted into a voice signal, which is supplied to the voice processing unit 18. The trainer voice data A / D converted by the voice processing unit 18 is stored in the trainer voice data storage area 14c of the storage unit 14 in time series (step S2).

When the reproduction of the accompaniment data is completed, the CPU 11 reads the trainer voice data stored in the trainer voice data storage area 14c, performs voice analysis processing on the read trainer voice data, and sets a pitch corresponding to the time. Calculation is made from the trainee voice data (step S3).
Subsequently, the CPU 11 compares the calculated pitch with the pitch of the melody data included in the accompaniment data stored in the accompaniment data storage area 14a of the storage unit 14 for each predetermined section (comparison section). The number of pitch points (difference information) indicating the degree of difference between the two is generated for each section (step S4).

Further, the CPU 11 reads the trainer voice data stored in the trainer voice data storage area 14c, performs voice recognition processing on the read trainer voice data, and recognizes the voice represented by the trainer voice data. Then, a recognized character string corresponding to the recognized voice is generated (step S5). Then, the CPU 11 compares the generated recognized character string with the lyrics data stored in the lyrics data storage area 14b for each section, and generates a lyrics score (difference information) indicating the degree of difference between the two for each section. (Step S6). By the processing in step S4 and step S6, the difference information indicating the scoring result for each section as illustrated in FIG. 3 is generated.
The CPU 11 transmits the pitch score and the lyrics score for each section generated in step S4 as scoring result data to the server device 3 via the communication network 4 (step S7). At this time, the CPU 11 also transmits a music code for identifying the music together with the scoring result data.

FIG. 8 is a flowchart showing the flow of processing performed by the server device 3. When the CPU 31 of the server device 3 detects that the scoring result data and the song code have been received via the communication network 4, the received scoring result data (difference information) is stored in the scoring result database storage area 34a of the storage unit 34. Store (step SB1).
Then, the CPU 31 calculates the “number of errors” and the “error rate” for each section by using the statistics of the pitch score and the lyrics score of the scoring result data for each section (step SB2). Specifically, for example, as statistical processing of the number of pitch points, the number of pitch points stored in the pitch scoring result table of the scoring result database is counted for each section whose pitch score is 60% or less. The count result is stored in the item “number of errors” in the pitch scoring result table. Further, for each section, a value obtained by dividing the number of errors by the total number of singings in the number of pitch points is stored in the item of “error rate”.
For the lyrics score, the same statistical processing is performed as the lyrics score, and the “number of errors” and “error rate” of the lyrics for each section are entered in the items of “number of errors” and “error rate” in the lyrics scoring result table Remember each.
As described above, the statistical processing (number of errors, error rate) for each section as shown in FIG. 5 is obtained by performing the above-described statistical processing for each of the pitch score and the lyrics score.
By performing statistical processing for each section in this way, it is possible to specify a section in which many people are mistaken for each viewpoint (pitch, lyrics, etc.), that is, a section that is easily mistaken.

  Next, the CPU 31 of the server device 3 extracts a section in which statistical results (number of errors, error rate) obtained by taking statistics of difference information (number of pitch points, number of lyrics) for each section satisfy a predetermined condition ( Step SB3). Specifically, for example, a predetermined number of sections are extracted as sections that are likely to be mistaken in order from a section having a large number of mistakes. Or you may make it extract the area where an error rate is larger than a predetermined threshold value. Further, as another example, it may be determined by extracting from the top of the error rate to what number. Alternatively, an average value of points may be calculated for each section, and a predetermined number of sections may be extracted from the lower value. Alternatively, an average score may be calculated for each section, and a section where the average score is smaller than a predetermined threshold may be extracted. In short, it is only necessary to extract a section in which a statistical result satisfies a predetermined condition.

  The CPU 31 of the server device 3 stores the section designation information indicating the extracted section in the section designation information storage area 34b. At this time, the CPU 31 may output the section designation information by transmitting the section designation information to the karaoke apparatus 2 via the communication network 4 (step SB4).

<A-2-2: Notification operation>
Next, the notification operation of section designation information will be described.
The practitioner operates the operation unit 16 of the karaoke apparatus 2 to select a song to be sung.
When the karaoke device 2 detects that a song has been selected via the operation unit 16, the karaoke device 2 transmits request information indicating that information indicating a section that is likely to be mistaken in the song is acquired prior to the singing by the communication network. 4 to the server device 3 via
When detecting that the request information has been received via the communication network 4, the CPU 31 of the server device 3 searches the section designation information storage area 34b for the song code of the song corresponding to the received request information, and the retrieved song code. The section designation information stored in association with is transmitted to the karaoke apparatus 2 via the communication network 4.

When the CPU 11 of the karaoke apparatus 2 detects that the section designation information has been received via the communication network 4, the CPU 11 causes the display unit 15 to display a screen for allowing the practitioner to select the notification mode.
FIG. 9 is a diagram illustrating an example of a screen displayed on the display unit 15. As shown in the figure, a screen that prompts the user to select one of “notify an easily mistaken part during singing”, “practice an easily mistaken part”, and “alternate an easily mistaken part” is displayed on the display unit 15. The practitioner operates the operation unit 16 while checking the screen displayed on the display unit 15, and selects one of these.

  In the screen shown in FIG. 9, when “notify an easily mistaken part during singing” is selected, the CPU 11 of the karaoke apparatus 2 reads the accompaniment data of the designated song from the accompaniment data storage area 14 a, and an audio processing unit 18 is supplied. The audio processing unit 18 converts the supplied accompaniment data into an analog signal (accompaniment sound signal) and supplies the analog signal to the speaker 19 for sound emission. At this time, the CPU 11 recognizes which position of the music the accompaniment sound signal generated by the sound processing unit 18 is. Specifically, for example, the CPU 11 recognizes this recognition process from the measure number information included in the accompaniment data supplied to the audio processing unit 18.

  The CPU 11 compares the recognized position (measure) with the start position (measure) of the section designation information acquired from the server device 3, and when the difference between the two becomes a predetermined difference (1 phrase in this embodiment). In addition to notifying the section indicated by the section specifying information, a preset mode is notified according to the feature data included in the section specifying information. The preset mode may be, for example, a mode in which the volume of the guide melody is increased in a section where the feature data is “pitch error”. Further, for example, with respect to the section in which the feature data is “Lyrics mistake”, it is possible to enlarge the characters displayed in the lyrics, add color to the characters, or display a dot on the upper part of the characters. Alternatively, for example, the display unit 15 may be configured to display a message such as “Be careful with lyrics for the next phrase” on the screen. In short, any information may be used as long as it is a notification in a preset manner according to the feature data. Note that the predetermined mode is not limited to one mode, and a mode in which the lyrics are bolded one by one and a mode in which the lyrics are simply stopped may be selected.

FIG. 10 is a diagram illustrating an example of a notification mode of section designation information. In this example, the section designation information is information indicating the section of the part “mother's back” of the lyrics, and an example of a notification mode when the feature data is “Lyrics mistake” is shown. In this case, the CPU 11 reads out the accompaniment data from the accompaniment data storage area 14a according to the progress of the music and supplies it to the audio processing unit 18, and reads out the lyrics data corresponding to the supplied accompaniment data from the lyrics data storage area 14b. This is supplied to the display unit 15. The audio processing unit 18 emits an accompaniment sound signal from the speaker 19 based on the supplied accompaniment data, and the display unit 15 controls the lyrics telop A1 corresponding to the lyric data as shown in FIG. Is displayed.
At this time, the CPU 11 specifies the start position of the section designation information based on the section number included in the section designation information acquired from the server device 3. Then, the CPU 11 compares the position of the accompaniment sound signal with the start position of the section designation information, and when the difference between the two becomes a predetermined difference (1 phrase in this embodiment), the feature included in the section designation information. Depending on the data, the letter A11 of the lyrics corresponding to the section indicated by the section designation information is enlarged and displayed on the display unit 15, and the practitioner's attention such as “Let's pay attention to the lyrics for the next phrase” is displayed. A prompt message A12 is displayed on the display unit 15.

  In this way, because it is informed of easy to make mistakes in the lyrics and pitch (pitch), the practitioner can know in advance what kind of mistakes are likely to be made in the section to be sung, even when singing for the first time. You can sing with care.

  Moreover, in this embodiment, the location which is easy to make an error is specified based on the statistical result of the past singer. Although there are some individual differences in the places where mistakes are likely to occur, they are often similar, so by taking statistics of past singers, it is possible to more accurately identify places where mistakes are likely to be made.

Next, in the screen shown in FIG. 9, when the “practice part that is easy to mistake” mode is selected, the CPU 11 first displays a list of sections indicated by the section designation information acquired from the server device 3. To display.
FIG. 11 is a diagram illustrating an example of a screen on which a list of sections indicated by the section specifying information is displayed. As shown in the figure, the CPU 11 displays information of a plurality of sections indicated by the section designation information (number of bars, section characteristics (many lyrics errors, many pitch errors, etc.), lyrics corresponding to the sections, etc.). To be displayed on the display unit 15. The practitioner selects the section he / she wants to practice while confirming the screen displayed on the display unit 15. When detecting that the section has been selected, the CPU 11 reads out the accompaniment data corresponding to the selected section from the accompaniment data storage area 14 a and supplies it to the audio processing unit 18. The sound processing unit 18 converts the supplied accompaniment data into an analog signal and supplies it to the speaker 19 for sound emission.

  Thus, since the accompaniment of the part corresponding to the easily mistaken section is emitted, the practitioner can practice in advance a mistaken place even when singing for the first time.

Next, in the screen shown in FIG. 9, when the mode of “alternative singing easy to mistake” is selected, the CPU 11 reads out the accompaniment data of the designated song from the accompaniment data storage area 14 a, and the audio processing unit 18 is supplied. The sound processing unit 18 converts the supplied accompaniment data into an analog signal and supplies it to the speaker 19 for sound emission. At this time, the CPU 11 recognizes where the accompaniment sound signal generated by the audio processing unit 18 is based on the bar number information included in the accompaniment data.
At the timing when the recognized position (measure) matches the start position (measure) of the section designation information acquired from the server device 3, the CPU 11 sets the model voice data of the portion corresponding to the section indicated by the section designation information as model voice. The model audio data read from the data storage area 14 e is supplied to the audio processing unit 18. The voice processing unit 18 converts the supplied model voice data into an analog signal and supplies the analog signal to the speaker 19 for sound emission. That is, both the accompaniment sound and the model voice are emitted in the section indicated by the section designation information acquired from the server device 3, while the accompaniment sound is generated in a section other than the section indicated by the section designation information acquired from the server device 3. Only play.

  In this way, the model voice is emitted in the section where mistakes are likely to occur, so that the karaoke apparatus 2 can emit the singing voice on behalf of the practitioner at the place where mistakes are difficult (difficult). In other words, the practitioner sings most of the tunes himself, but the karaoke device 2 sings with a model voice instead of singing difficult (prone to mistakes) by himself. As a result, the practitioner does not need to sing difficult parts in the song himself, and even if it is a song that contains difficult parts and is considered difficult to sing, it will challenge the song. be able to.

<B: Second Embodiment>
Next explained is the second embodiment of the invention.
This embodiment differs from the first embodiment described above in that the data stored in the storage unit of the karaoke device is different from the scoring process performed by the karaoke device, and the other configurations are as follows. This is the same as in the first embodiment described above. Therefore, in the following description, the same components as those in the first embodiment described above are denoted by the same reference numerals and the description thereof is omitted.

FIG. 12 is a diagram illustrating an example of a hardware configuration of the karaoke apparatus 2A according to this embodiment. In the figure, in the model technique data storage area 14f of the storage unit 14, data indicating the type and timing of the singing technique used in the model singing represented by the model voice data stored in the model voice data storage area 14e. (Hereinafter "exemplary technique data") is stored. In the present embodiment, this model technique data is used as model data.
FIG. 13 is a diagram illustrating an example of the contents of model technique data. As illustrated, in the exemplary technique data, items of “section information” and “type information” are associated with each other. Among these items, the “section information” item stores information indicating a section in which the singing technique is used in the model voice data. The section indicated by the section information may be a section having a time width represented by the start time information and the end time information, or may indicate a certain point of time.
In the “type information” item, information for identifying a plurality of types of singing techniques set in advance is stored. This “type information” is information for identifying a singing technique such as “vibrato”, “shakuri”, “fist”, “farset”, “tsukkomi”, “for”, “breathing”, and the like. “Vibrato” refers to a technique that raises and lowers the pitch of the sound only slightly and produces a trembling tone. “Shikkuri” refers to a technique in which sound is generated from a sound lower than the target sound, and the pitch is smoothly brought close to the target sound. “Fist” refers to a technique for adding a decorative undulation. “Falset” indicates a technique of singing with a so-called “back voice”. “Tsukumi” refers to a technique for making the singing start earlier than the original timing. “For” indicates a technique for making the singing timing later than the original timing. The “breathing” indicates the timing when the singer breathes.
The practitioner technique data storage area 14g stores data indicating the singing technique used in the practitioner voice data (hereinafter, “practice technique data”). The structure of this practicer technique data is the same as that of the model technique data described above, and the items “section information” and “type information” are associated with each other.

FIG. 14 is a diagram showing an example of the contents of scoring result data.
As shown in the figure, the scoring result data includes singing technique scoring results such as “vibrato score” and “scribbing score” in addition to the “pitch score” and “lyric score” shown in the first embodiment. Stored for each section (comparison section).

Next, the scoring result statistical operation of this embodiment will be described below with reference to the flowchart shown in FIG.
When the practitioner operates the operation unit 16 of the karaoke apparatus 2A to select a song, a signal indicating the selection content is output from the operation unit 16 to the CPU 11. When the CPU 11 detects that the signal indicating the operation content has been input, the CPU 11 reads out the model voice data corresponding to the selected song from the model voice data storage area 14e of the storage unit 14, and performs voice processing on the read model voice data. Analysis processing is performed, and the pitch, power, and spectrum corresponding to the time are calculated from the model voice data (step SC1). Subsequently, the CPU 11 analyzes the melody data included in the accompaniment data stored in the accompaniment data storage area 14a and the model voice data stored in the model voice data storage area 14e in units of predetermined frames, A temporal correspondence with the melody data is detected (step SC2).
Next, the CPU 11 analyzes the pattern of temporal change in pitch, power, and spectrum calculated from the model voice data, determines whether or not this analysis result corresponds to a predetermined pattern, and When doing so, the section corresponding to the pattern is specified as a section in which a specific singing technique is used. Then, the CPU 11 stores the section information of the specified section in the exemplary technique data storage area 14f of the storage unit 14 in association with the type information indicating the singing technique (step SC3).

  Here, the specific process of the section in which each singing technique is used shown in step SC3 will be described below. In the present embodiment, the CPU 11 specifies (detects) a section in which each singing technique of “vibrato”, “shakuri”, “fist”, “farset”, “tsukkomi”, “for” and “breathing” is used. ) Among these, “vibrato” and “shrimp” are detected based on the pitch calculated from the model voice data. “Fist” and “Falset” are detected based on the spectrum calculated from the model voice data. Further, “for” and “tsukkomi” are detected based on the pitch and melody data calculated from the model voice data. Further, “breathing” is detected based on the power calculated from the model voice data and the melody data.

Based on the correspondence between the model voice data and the melody data and the pitch calculated from the model voice data, the CPU 11 starts the sound of the sound included in the model voice data and the start of the sound of the melody data corresponding to the sound. Specify a section with a different time. Here, the CPU 11 is a section in which the pitch change timing of the model voice data appears earlier than the pitch change timing of the melody data, that is, the start time of the sound included in the model voice data is the melody data corresponding to the sound. For a section earlier than the start time of the sound, this section is specified as a section in which the “Tsukumi” singing technique is used. The CPU 11 stores the section information of the specified section in the exemplary technique data storage area 14 f of the storage unit 14 in association with the identification information indicating “push”.
Conversely, the CPU 11 delays the pitch change timing of the model voice data from the pitch change timing of the melody data based on the correspondence between the model voice data and the melody data and the pitch calculated from the model voice data. , That is, a section where the start time of the sound included in the model voice data is later than the start time of the sound of the melody data corresponding to the sound, and the singing technique of “for” is used for the detected section It is specified that it is a section that has been.

  Further, the CPU 11 analyzes a pattern of temporal change of the pitch calculated from the model voice data, detects a section where the pitch continuously fluctuates within a predetermined range above and below the central frequency, The detected section is identified as a section in which the “vibrato” singing technique is used.

  Further, the CPU 11 analyzes the pattern of the temporal change of the pitch calculated from the model voice data, detects a section where the pitch continuously changes from a low pitch to a high pitch, and detects the detected section as “shrunk”. It is specified that it is a section in which the singing technique is used. This process may be performed based on the correspondence with the melody data. In other words, the CPU 11 may detect a section in which the pitch of the model voice data is continuously approaching the pitch of the melody data from a low pitch based on the correspondence relationship between the model voice data and the melody data.

  Further, the CPU 11 is a section in which the melody data is sound and the power value of the model voice data is predetermined based on the correspondence between the model voice data and the melody data and the power calculated from the model voice data. A section smaller than the threshold is detected, and the detected part is identified as a "breathing" section.

In addition, the CPU 11 analyzes the temporal change pattern of the spectrum calculated from the model voice data, detects a section where the spectrum characteristic is abruptly changed to the predetermined change state, and detects the detected section. It is specified that the section uses the “Falset” singing technique. Here, the predetermined change state is a state in which the harmonic component of the spectrum characteristic is extremely reduced. For example, as shown in FIG. 16, in the case of a local voice, many harmonic components are included (refer to FIG. 16A), but when a falset is formed, the magnitude of the harmonic components becomes extremely small (FIG. b)). In this case, the CPU 11 may also refer to whether or not the pitch has changed significantly upward. The falset is sometimes used even when generating the same pitch as the local voice, but is generally a technique used when generating high-pitched sounds that cannot be generated by the local voice. Therefore, “Falset” may be detected only when the pitch of the audio data is equal to or higher than a predetermined pitch. In addition, since the pitch range using the falset is generally different between male voice and female voice, gender detection is performed based on the voice data range and formants detected from the voice data, and based on this result, the pitch range for falset detection is determined. It may be set.
In addition, the CPU 11 detects a section in which the mode of change of the spectrum characteristic is variously switched in a short time, and identifies the detected part as a part where the “fist” singing technique is used. In the case of “fist”, it is a singing technique that adds a taste that changes the voice color and utterance method in a short section, so the spectral characteristics change variously in the section where this technique is used. .
As described above, the CPU 11 detects the section in which each singing technique is used from the model voice data, associates the section information indicating the detected section with the type information indicating the singing technique, and stores the model technique in the storage unit 14. Store in the data storage area 14f.

  Returning to the description of FIG. CPU11 of 2A of karaoke apparatuses will read the accompaniment data memorize | stored in the accompaniment data storage area 14a, and will supply the read accompaniment data to the audio | voice processing part 18, after the production | generation process (step SC3) of model technique data is complete | finished. The sound processing unit 18 converts the supplied accompaniment data into an analog signal and causes the speaker 19 to sound the sound represented by the accompaniment data. In addition to supplying accompaniment data to the audio processing unit 18, the CPU 11 supplies the lyrics data stored in the lyrics data storage area 14b to the display unit 15 and displays lyrics corresponding to the accompaniment to be reproduced. 15 is displayed.

  The practitioner sings along with the accompaniment sounded from the speaker 19 while confirming the lyrics displayed on the display unit 15. When the practitioner sings, the practitioner's voice is converted into a voice signal by the microphone 17, and the converted signal is output to the voice processing unit 18. The voice processing unit 18 converts the voice signal output from the microphone 17 into digital data to obtain trainer voice data (step SC4). The trainer speech data is output from the speech processing unit 18 and stored in the trainer speech data storage area 14c of the storage unit 14.

  When reproduction of the accompaniment is completed, the CPU 11 of the karaoke apparatus 2A performs basic analysis processing on the trainer speech data stored in the trainer speech data storage area 14c to calculate the pitch, power, and spectrum (step SC5). ). Further, the CPU 11 of the karaoke apparatus 2A analyzes the melody data included in the accompaniment data stored in the accompaniment data storage area 14a and the practitioner voice data stored in the practitioner voice data storage area 14c in a predetermined frame unit. Then, the temporal correspondence between the trainer voice data and the melody data is detected (step SC6). Subsequently, the CPU 11 generates trainer technique data from the trainer voice data (step SC7). The difference between the processing shown in steps SC5 to SC7 and the processing shown in steps SC2 to SC4 described above is that the audio data to be processed is different. That is, in step SC2 to step SC4, the process is performed on the model voice data, and in steps SC5 to SC7, the process is performed on the trainer voice data. Detailed description of SC7 will be omitted.

  Next, the CPU 11 of the karaoke apparatus 2A directly compares the waveforms of both the model voice data and the trainer voice data, and uses, for example, DTW (Dynamic Time Warping) to Are associated with each other for each frame, and the corresponding location of both is detected (step SC8).

  Subsequently, the CPU 11 of the karaoke apparatus 2A compares the model voice data stored in the model voice data storage area 14e with the practitioner voice data output from the voice processing unit 18 based on the corresponding part detected in step SC8. Then, difference information indicating the degree of difference between the trainer voice data and the model voice data is generated for each section (step SC9). Specifically, the CPU 11 compares the pitch of the model voice data and the pitch of the trainer voice data for each section, and displays difference information indicating the degree of difference between the trainer voice data and the model voice data for each section. The generated difference information is stored in the scoring result data storage area 14d. Further, the CPU 11 reads the model technique data stored in the model technique data storage area 14f of the storage unit 14 one by one, and searches the trainer technique data storage area 14g for the trainer technique data corresponding to the read model technique data. Then, the model technique data and the practitioner technique data are compared for each section, and difference information indicating the degree of difference between the two is generated and stored in the scoring result data storage area 14d. Then, the CPU 11 transmits the generated scoring result data to the server device 3 via the communication network 4 (step SC10).

  When detecting that the scoring result data has been received via the communication network 4, the server device 3 stores the received scoring result data in the scoring result database storage area 34a of the storage unit 34, and the statistics of the scoring result data are stored in the section. For each section, the statistical results (number of errors, error rate) of the lyrics, pitches, and singing techniques (vibrato, fist, etc.) for each section are calculated. Although this process is different from the process shown in steps SB1 and SB2 in FIG. 8 and the data (pitch, lyrics, singing technique) to be processed, the general process flow is the same as that described above. The description is omitted here.

  As described above, in this embodiment, in addition to the pitch and the lyrics, the differences in the singing technique are extracted, so the practitioner can be notified of the differences in the singing technique, and more detailed information can be practiced. The person can be notified.

<C: Modification>
As mentioned above, although embodiment of this invention was described, this invention is not limited to embodiment mentioned above, It can implement with another various form. An example is shown below.
(1) In the above-described embodiment, a specific section (a section that is easily mistaken) is notified to the practitioner by increasing the volume of the guide melody or increasing the text of the lyrics. The form of notification is not limited to this. For example, it may be a form that outputs a voice message or warning sound to call attention, or a list of sections that are likely to be mistaken is displayed before the start of accompaniment sound emission. It may be a form to do. In short, any notification form that can convey a message or information to the practitioner by some means may be used.

  Further, in the above-described embodiment, notification in a preset mode is performed according to the feature data included in the section designation information. However, the section designation information may not include feature data. In this case, the CPU of the karaoke apparatus may notify the section (for example, a phrase number or measure number) indicated by the section designation information without performing a caution display such as “attention to lyrics”.

(2) As a scoring operation performed by the CPU 11 of the karaoke apparatus 2, the trainer voice data and the melody data are compared in the first embodiment, while the trainer voice data and the model voice data are compared in the second embodiment. The scoring was done by comparison. Either one of the scoring methods may be used, or both may be used for scoring processing. In the above-described embodiment, the pitch, lyrics, or singing technique of the voice is compared for each section. However, the present invention is not limited to this. The formants may be detected for each of the data, and the voice quality may be compared for each section for scoring.

(3) In the above-described embodiment, the section number included in the section designation information is a number assigned to each measure in units of one measure, but the unit section is not limited to a measure. One phrase may be used as a unit, or a note may be used as a unit. In short, any unit may be used as long as it is a predetermined unit.
In the embodiment described above, the CPU 11 of the karaoke device 2 compares the position (measure) recognized from the measure number information included in the accompaniment data and the start position (measure) of the section designation information acquired from the server device 3. However, when the difference between the two becomes one phrase, the section indicated by the section designation information is notified. The “difference between the two” in this case is not limited to “1 phrase”, and may be, for example, 2 phrases or 1 measure. In short, when the difference between the two becomes a predetermined difference, the section indicated by the section designation information may be notified.

  Further, in the above-described embodiment, the CPU 11 of the karaoke apparatus 2 recognizes where the accompaniment sound signal generated by the audio processing unit 18 corresponds to the measure number information included in the accompaniment data. However, the method for recognizing the position of the accompaniment sound signal is not limited to this. For example, the accompaniment sound signal generated by the sound processing unit 18 in accordance with the accompaniment data reading process by the CPU 11 is the position of the music. You may make it recognize whether it corresponds to a position. Specifically, for example, the CPU of the karaoke apparatus recognizes the accompaniment data read from the storage unit and supplied to the sound processing unit by integrating the length of the note (or rest) supplied. It may be. Alternatively, the CPU 11 may count the tempo clock and count the number of beats from the beginning of the song. Also, the integrated value of notes and beats (or measures and phrases) can be converted to time if the tempo speed is known, so the time data from the beginning of the song is used to indicate the position of the accompaniment sound signal in the song. May be recognized. In this case, the portion corresponding to the “section number” (see FIG. 8) included in the difference information and the section designation information in the embodiment corresponds to the position recognition of the accompaniment sound signal, and the notes (rests) from the beginning of the song. Data) indicating the cumulative length of the song, the number of beats from the beginning of the song, or the elapsed time from the beginning of the song.

(4) In the embodiment described above, difference information indicating the degree of difference is calculated as a scoring result. Instead of this, the comparison data itself (for example, a pitch shift amount) may be used.

(5) In the above-described embodiment, the case where the practitioner's singing is evaluated has been described as an example. However, the present invention is not limited thereto, and the practitioner's musical instrument performance may be evaluated. In this case, the trainer voice data is data representing the performance sound of the input musical instrument, and the performance data of the musical instrument other than the musical instrument to be practiced is stored in the accompaniment data storage area 14a. The area 14e stores data representing the performance sound of a musical instrument used as a model.

(6) In the above-described embodiment, the audio data stored in the exemplary audio data storage area 14e of the storage unit 14 is data in the WAVE format or the MP3 format, but the data format is not limited to this. Any type of data may be used as long as it indicates data.
In the above-described embodiment, the model voice data is stored in the model voice data storage area 14e, and the CPU 11 of the karaoke apparatus 2 reads the model voice data from the model voice data storage area 14e. Thus, the audio data may be received via a communication network. In short, the model audio data may be input to the CPU 11.
In the first embodiment described above, melody data representing the melody pitch (pitch) of various musical instruments that accompany the music is used as the model data. The model data is not limited to this, and any data may be used as long as it represents the melody pitch of the music, such as a music melody, sub melody, or chorus.

(7) In the first embodiment described above, a recognition character string corresponding to the speech recognized by performing speech recognition processing on the trainer speech data is generated, and the generated recognition character string and lyric data are generated for each section. Compared to the detected lyrics mistakes. Instead of this, the spectrum of the model voice data and the trainer voice data may be calculated for each section, and the corresponding part of the spectrum may be compared to detect the lyric error.

(8) In the above-described embodiment, the music practice system 1 in which the karaoke device 2 and the server device 3 are connected via a communication network realizes the function according to the above-described embodiment. On the other hand, three or more devices connected via a communication network may share the above functions, and a system including the plurality of devices may realize the system of the embodiment. Alternatively, one device may realize all of the above functions.

(9) The program executed by the CPU 11 of the karaoke apparatus 2 or the CPU 31 of the server apparatus 3 in the above-described embodiment is a magnetic tape, a magnetic disk, a flexible disk, an optical recording medium, a magneto-optical recording medium, or a CD (Compact Disk)- It can be provided in a state stored in a recording medium such as a ROM, a DVD (Digital Versatile Disk), or a RAM. It is also possible to download to the karaoke apparatus 2 or the server apparatus 3 via a network such as the Internet.

It is a block diagram which shows an example of a structure of a music practice system. It is a block diagram which shows an example of the hardware constitutions of a karaoke apparatus. It is a figure which shows an example of the content of scoring result data. It is a block diagram which shows an example of the hardware constitutions of a server apparatus. It is a figure which shows an example of the content of the pitch scoring result table. It is a figure which shows an example of the content of area designation information. It is a flowchart which shows the flow of the process which CPU of a karaoke apparatus performs. It is a flowchart which shows the flow of the scoring result statistical process which CPU of a server apparatus performs. It is a figure which shows an example of the screen displayed on the display part of a karaoke apparatus. It is a figure which shows an example of the alerting | reporting aspect of the area which section designation information shows. It is a figure which shows an example of the screen displayed on the display part of a karaoke apparatus. It is a figure which shows an example of the hardware constitutions of the karaoke apparatus which concerns on 2nd Embodiment of this invention. It is a figure which shows an example of the content of model technique data. It is a figure which shows an example of the content of scoring result data. It is a flowchart which shows the flow of the process which CPU of a karaoke apparatus performs. It is a figure for demonstrating the detection process of a false set.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Music practice system, 2, 2a, 2b, 2c ... Karaoke apparatus, 3 ... Server apparatus, 4 ... Communication network, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ... Memory | storage part, 15 ... Display part, 16 DESCRIPTION OF SYMBOLS ... Operation part, 17 ... Microphone, 18 ... Audio | voice processing part, 19 ... Speaker, 20 ... Communication part, 31 ... CPU, 32 ... ROM, 33 ... RAM, 34 ... Memory | storage part, 35 ... Communication part.

Claims (12)

Accompaniment data storage means for storing accompaniment data constituting the accompaniment sound of the music;
Obtaining means for obtaining section designation information indicating a specific section of the music;
Instruction means for instructing the start of the accompaniment;
An accompaniment sound signal generating means for reading accompaniment data from the accompaniment data storage means in accordance with the progress of the music and generating an accompaniment sound signal based on the read accompaniment data when the instruction means instructs to start an accompaniment; ,
Accompaniment position recognition means for recognizing which position of the music the accompaniment sound signal generated by the accompaniment sound signal generation means is;
The position recognized by the accompaniment position recognition means is compared with the start position of the section designation information acquired by the acquisition means, and when the difference between the two becomes a predetermined difference, the section indicated by the section designation information is notified. A music practice device comprising: a notification means. The section designation information includes feature data indicating characteristics of a section to be specified, and the notification unit performs notification of a mode set in advance according to the feature data together with notification of the section. The music practice device according to 1. Accompaniment data storage means for storing accompaniment data constituting the accompaniment sound of the music;
Model voice data storage means in which model voice data representing melodic sounds included in the music is stored;
Obtaining means for obtaining section designation information indicating a specific section of the music;
Instruction means for instructing the start of the accompaniment;
An accompaniment sound signal generating means for reading accompaniment data from the accompaniment data storage means in accordance with the progress of the music and generating an accompaniment sound signal based on the read accompaniment data when the instruction means instructs to start an accompaniment; ,
Accompaniment position recognition means for recognizing which position of the music the accompaniment sound signal generated by the accompaniment sound signal generation means is;
Model voice data corresponding to the section indicated by the section designation information acquired by the acquisition means at the timing when the position recognized by the accompaniment position recognition means matches the start position of the section designation information acquired by the acquisition means And a sound signal generating means for generating a sound signal based on the read model sound data. Accompaniment data storage means for storing accompaniment data constituting the accompaniment sound of the music;
Obtaining means for obtaining section designation information indicating a specific section of the music;
Specific section instructing means for instructing the start of accompaniment from the section indicated by the section specifying information acquired by the acquiring means;
When the start of the accompaniment is instructed by the specific section instruction means, the accompaniment data of the portion corresponding to the section indicated by the section designation information acquired by the acquisition means is read from the accompaniment data storage means, and the read accompaniment data is A music practice device comprising: accompaniment sound signal generation means for generating an accompaniment sound signal based on the music sound. The accompaniment data includes position information indicating the position of the music, and the accompaniment position recognizing means uses the accompaniment sound signal generated by the accompaniment sound signal generating means from the position information included in the accompaniment data. The music practice device according to any one of claims 1 to 3, wherein the position is recognized. The accompaniment position recognizing means recognizes in which position of the music the accompaniment sound signal generated by the accompaniment sound signal generating means corresponds to a process of reading accompaniment data by the accompaniment sound signal generating means. The music practice device according to any one of claims 1 to 3. Input means for accepting input of trainee data representing the trainee's voice;
The input practice data and the model data stored in the model data storage means are compared for each comparison section in a predetermined time unit, and difference information indicating the degree of difference between the two is provided for each comparison section. The music practice device according to claim 1, further comprising a comparison unit that generates and outputs the comparison unit. The exemplary data is data representing the melody pitch of the music,
Pitch calculation means for calculating the pitch of the voice from the trainee data;
The comparison means compares the pitch calculated by the pitch calculation means and the pitch indicated by the model data stored in the model data storage means for each comparison section, and shows difference information indicating the degree of difference between the two. The music practice device according to claim 7, wherein: is generated for each comparison section. The exemplary data is data representing the lyrics of the music,
Voice recognition means for recognizing the voice represented by the trainee data and generating a recognized character string corresponding to the recognized voice;
The comparison unit compares the recognized character string generated by the voice recognition unit and the model data stored in the model data storage unit for each comparison section, and displays difference information indicating the degree of difference between the two. It produces | generates for every said comparison area. The music practice apparatus of Claim 7 characterized by the above-mentioned.   The music practice device according to claim 7, wherein the model data is technique data indicating a type and timing of a technique used for a model song.   8. The music practice according to claim 7, wherein the practitioner data is data representing a performance sound of an input musical instrument, and the model data is data representing a performance sound of a musical instrument used as a model. apparatus. A plurality of music practice devices according to any one of claims 7 to 11,
The difference information generated by the comparison means of each music practice device is received via a network, and the statistics of the received difference information are taken for each comparison interval, and a comparison interval satisfying a predetermined statistical result is extracted. A server device having section designation information generating means for generating section designation information indicating the extracted comparison section as a specific section of the music;
The music practice system according to claim 1, wherein the acquisition unit of each music practice device obtains section designation information from the server device.

Images