JP2007310204A - Musical piece practice support device, control method, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a person who practices singing a song or performing a musical instrument with model sounds imitating a desired model person's singing voice or performing sound. <P>SOLUTION: When a musical piece ID and a model person ID are selected by a practicing person, the control section 21 of a KARAOKE device 2 transmits the selected musical piece ID and the model person ID to a server device 3 through a communication section 28. The control section 31 of the server device 3 reads guide voice data corresponding to the selected musical piece ID out of a voice data storage area 32a, reads characteristic data corresponding to the selected model person ID out from a characteristic data storage area 32d, and processes a part of the readout guide voice data corresponding to the readout characteristic data on the basis of the characteristic data. Then, the control section 31 transmits the processed guide voice data to the KARAOKE device 2. The KARAOKE device 2 plays the sound of the received guide voice data. <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to a music practice support device, a control method, and a program.

  People who practice singing often practice singing using a karaoke device that displays lyrics on the screen and reproduces the accompaniment of the music. Some of such karaoke apparatuses have a so-called “guide vocal function” that reproduces an exemplary singing voice. If this guide vocal function is used, the practitioner can audition how to sing the music.

  By the way, a skilled singer like a singer rarely sings according to the content of the score, many of which intentionally shift the beginning and end of singing, change the voice quality and volume, or Express emotions in the song by using various singing techniques such as vibrato and fist. Such feelings are expressed in various ways by the singer. For example, a singer who always puts the vibrato at the end of the phrase, a singer who always tries to start singing (shifts the timing), or sings the treble with a falsetto. There are also singers who perform, and each singer is often characterized by its way of singing. People who practice singing often want to imitate the unique singing method of their favorite singers.

  However, the singing voice that is played by the above-mentioned guide vocal function is often not the singer's singing voice that the practitioner is aiming for. Often there are considerable gaps. When the way of singing with guide vocals is far from the way of singing, the desire to improve the trainer is often lowered. This applies not only to the singing of music but also to the performance of musical instruments.

As a system for supporting utterance practice, for example, Patent Document 1 proposes a system that converts an utterance voice of a model (teacher) into a voice of a practitioner (student) and listens to it. Further, Patent Document 2 proposes a system that reproduces an utterance voice of a trainee by performing a voice process such as correcting a spectrum envelope.
JP 2002-244547 A JP 2004-133409 A

However, in the system described in Patent Document 1, it is necessary for the practitioner himself to select which model voice to practice, which is complicated for the practitioner. Further, in the system described in Patent Document 2, since speech processing is performed on the speech sound of the practitioner, unnatural pronunciation may occur.
The present invention has been made under the above-described background, and an object thereof is to provide a singing voice or performance sound simulating a favorite model person's singing voice or performance sound to those who practice singing or playing. .

A music practice support device according to a preferred aspect of the present invention stores a plurality of feature data blocks including one or a plurality of feature data indicating features of a specific part in the progress of a singing voice or a musical instrument performance sound. Feature data storage means for storing a plurality of identification information for identifying each of the data blocks, and a guide voice for storing a plurality of sets in association with song identification information for identifying a song and guide voice data representing the singing voice or performance sound of the song A data storage means; an input receiving means for receiving input of the identification information and the music identification information; and a guide for reading out guide voice data corresponding to the music identification information received by the input receiving means from the guide voice data storage means. Feature data corresponding to the identification information received by the voice data reading means and the input receiving means A feature data reading means for reading feature data included in the lock from the feature data storage means, and a portion corresponding to the feature data read by the feature data reading means for the guide voice data read by the guide voice data reading means. , Guide voice data processing means for processing based on the feature data, and output means for outputting the guide voice data processed by the guide voice data processing means.
In this aspect, the specific part may be a part where a singing technique or a performance technique is used.
In this aspect, the specific portion may be a portion in which at least one of a technique of vibrato, sneeze, fist, falsetto, pricking, and breathing is used.

  ADVANTAGE OF THE INVENTION According to this invention, the singing voice or performance sound imitating a favorite model person's singing voice or performance sound can be provided to those who practice singing or performing.

Next, an embodiment of the present invention will be described.
In the following description, a person who practices singing is called a “practicing person”, and a person who performs singing that serves as an example for the practicing person is called a “executive person”.
<A: Configuration>
FIG. 1 is a block diagram showing the overall configuration of a music practice support system 1 according to this embodiment. This music practice support system 1 includes a plurality of karaoke apparatuses 2a, 2b, 2c, a server apparatus 3, and a network 4 connecting them. The karaoke devices 2 a, 2 b, 2 c are provided in various households such as ordinary households, karaoke boxes or restaurants, and function as communication devices that perform communication via the network 4. The server device 3 functions as a music practice support device that provides a practitioner with a singing voice imitating the singing voice of a model person who likes the practice person. The network 4 is, for example, ISDN (Integrated Services Digital Network) or the Internet, and includes a wired section or a wireless section. FIG. 1 illustrates three karaoke devices 2a, 2b, and 2c, but the number of karaoke devices included in the music practice support system 1 is not limited to three, and even more than this. It may be less. In the following description, when it is not necessary to distinguish the karaoke apparatuses 2a, 2b, and 2c, they are simply described as “karaoke apparatus 2”.

  FIG. 2 is a block diagram showing the configuration of the karaoke apparatus 2. In FIG. 2, the control unit 21 is, for example, a CPU, and controls each unit of the karaoke apparatus 2 by reading and executing a computer program stored in the storage unit 22. The display unit 23 is, for example, a liquid crystal display, 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 control unit 21. The operation unit 24 includes various keys and outputs a signal corresponding to the pressed key to the control unit 21. The microphone 25 collects the voice uttered by the practitioner. The sound processing unit 26 converts the sound (analog data) collected by the microphone 25 into digital data and outputs the digital data to the control unit 21. The speaker 27 emits sound output from the sound processing unit 26. The communication unit 28 performs data communication with the server device 3 via the network 4 under the control of the control unit 21.

  The storage unit 22 is a large-capacity storage unit such as a hard disk, and has an accompaniment / lyric data storage area 22a in addition to storing the computer program described above. In the accompaniment / lyric data storage area 22a, accompaniment data in which performance sounds of various musical instruments that accompany the music are recorded as the music progresses and lyrics data indicating the lyrics of the music are assigned to the music It is stored in association with the ID. The accompaniment data has a data format such as MIDI (Musical Instruments Digital Interface) format, and is reproduced when the practitioner sings a karaoke song. The lyrics data is displayed on the display unit 23 as a lyrics telop at the time of the karaoke song.

  Next, FIG. 3 is a block diagram showing a configuration of the server device 3. In FIG. 3, the control unit 31 is, for example, a CPU, and controls each unit of the server device 3 by reading and executing a computer program stored in the storage unit 32. The storage unit 32 is a large-capacity storage unit such as a hard disk. The communication unit 33 performs data communication with the karaoke apparatus 2 through the network 4 under the control of the control unit 31.

In addition to storing the computer program described above, the storage unit 32 stores a guide voice data storage area 32a, a musical score data storage area 32b, a technique insertion location designation data storage area 32c, and a feature data storage area 32d as shown in the figure. And have.
In the guide voice data storage area 32a, guide voice data representing a singing voice sung by a certain singer in accordance with the music accompaniment is stored in association with the music ID assigned to the music. The guide audio data is in a data format such as WAVE format or MP3 (MPEG Audio Layer-3) format. In the musical score data storage area 32b, musical score data representing a singing sound defined by the musical score of the music is stored in association with the music ID. The musical score data is in a data format such as a MIDI format, for example, and includes the pitch of the singing sound and its pronunciation timing.

In the technique insertion location designation data storage area 32c, technique insertion location designation data used in the processing of guide voice data to be described later is stored in association with the “music ID”.
FIG. 4 is a diagram illustrating an example of the contents of technique insertion location designation data. As shown in the figure, the technique insertion location designation data stores items of “technique type”, “time (timing)”, and “condition” in association with each other. Among these items, the item of “Technology Type” identifies singing techniques such as “Vibrato”, “Shakuri”, “Fist”, “Falset”, “Tsukumi”, “For”, “Breath”, etc. The identification information to be stored is stored. “Vibrato” is a technique that produces a trembling tone by raising and lowering the pitch of the sound only slightly. “Shikkuri” is 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” is a technique of performing a undulating curl that is decoratively added. “Falset” is a technique of singing with a so-called “back voice”. “Tsukumi” is a technique in which singing is performed at a timing earlier than the original timing. “Tame” is a technique in which singing is made later than the original timing. “Respiration” means the timing when the practitioner takes a breath.
Next, in the “timing” item, time information indicating the timing (part) at which the technique is inserted in the guide voice data is stored. Next, in the item “condition”, information indicating a condition for determining whether or not to insert the technique into the guide voice data is stored.

Next, in the feature data storage area 32d of the storage unit 32, a feature data block including feature data indicating features of a part in which the singing technique is used in the progression of the singing voice of the modeler is assigned to the modeler. It is stored in association with “exemplary ID”.
FIG. 5 is a diagram illustrating an example of the contents of the feature data block stored in the feature data storage area 32d. As shown in the figure, the feature data block includes a plurality of feature data in which items of “technique type” and “parameter” are associated with each other. In the example illustrated in FIG. 5, the feature data block including a plurality of feature data is illustrated. However, the feature data block may include one or more feature data.
Among the items of feature data, the “technique type” item stores identification information for identifying a technique, as in the “technique type” item of the technique insertion location designation data described above.
Information indicating an aspect of the technique is stored in the “parameter” item. In the example shown in FIG. 5, numerical values indicating the degree of the aspect of the technique in 10 levels are stored. For example, in the case of “Vibrato”, numerical values indicating the degree of “depth”, “speed”, “length”, and “frequency” of vibrato are stored in 10 levels. Numerical values indicating the degree of “gradient”, “pitch difference”, and “frequency” are stored in 10 levels. In the case of “push” and “for”, “timing difference” and “frequency” are displayed in 10 levels. In the case of “breathing” or “fist”, a numerical value indicating “length” in 10 stages is stored as the time length in which the technique is used. Further, in the case of “Falset”, information indicating the pitch that is the falset (back voice) is stored. For example, in the example shown in FIG. 5, the “vibrato” technique is such that “depth” is “3”, “speed” is “6”, “length” is “4”, and “frequency” is “5”. The data when used at a degree of "is stored.
In the example shown in FIG. 5, the mode of the technique is indicated by 10-stage numerical values, but the present invention is not limited to this, and any information may be used as long as the information indicates the mode of the technique.

<B: Operation>
Next, the operation of this embodiment will be described.
<B-1: Authoring operation>
First, an authoring operation in which a plurality of modelers sing a certain piece of music (hereinafter referred to as “reference music”) and the control unit 31 of the server device 3 generates a feature data block from each modeler's singing voice will be described. .
In the sequence diagram of FIG. 6, the model person operates the operation unit 24 of the karaoke apparatus 2 to instruct the reproduction of the karaoke accompaniment of the reference song. At this time, the modeler inputs his / her modeler ID through the operation unit 24, or the control unit 21 itself generates the modeler ID. And the control part 21 starts karaoke accompaniment (step S1). That is, the control unit 21 reads the accompaniment data from the accompaniment / lyric data storage area 22a and supplies the accompaniment data to the audio processing unit 26. The audio processing unit 26 converts the accompaniment data into an analog signal, supplies it to the speaker 27, and releases it. Let it sound. In addition, the control unit 21 reads out the lyric data from the accompaniment / lyric data storage area 22 a and causes the display unit 23 to display the lyrics telop. The model person sings along with the accompaniment emitted from the speaker 27. At this time, the voice of the model person is picked up by the microphone 25, converted into a voice signal, and output to the voice processing unit 26. The audio data A / D converted by the audio processing unit 26 (hereinafter “exemplary audio data”) is stored (recorded) in the storage unit 22 together with information indicating the elapsed time from the start of accompaniment (step S2). .

  When the reproduction of the accompaniment data ends, the control unit 21 ends the process of recording the model person's singing voice. Next, the control part 21 transmits the model audio | voice data memorize | stored in the memory | storage part 22 to the server apparatus 3 from the communication part 28 with said model person ID (step S3). When the control unit 31 of the server device 3 detects that the model voice data and the model ID are received by the communication unit 33, the control unit 31 stores the model voice data and the model ID in the storage unit 32. Next, the control unit 31 separates the model audio data stored in the storage unit 32 into frames of a predetermined time length, and calculates the pitch, sound generation timing, power, and spectrum in units of frames (step S4). Regarding the calculation of the sound generation timing, the timing at which a certain pitch changes to the next pitch may be considered as the sound generation timing. Further, for example, FFT (Fast Fourier Transform) may be used for the calculation of the spectrum.

  Next, the control unit 31 extracts a technique from the model voice data (step S5). First, the control unit 31 specifies (detects) a section in which each of these techniques is used. For example, “vibrato” and “shrimp” can be detected based on the pitch of the model voice data. Further, “fist” and “falset” can be detected based on the spectrum of the exemplary voice data. Further, “for” and “tsukkomi” can be detected based on the pitch of the model voice data and the score sound data stored in the score sound data storage area 32b. Further, “breathing” can be detected based on the power of the model voice data and the musical score data stored in the musical score data storage area 32b.

A specific detection method is as follows.
The control unit 31 is included in the model voice data based on the correspondence between the model voice data and the score sound data stored in the score data storage area 32b and the pitch calculated from the model voice data. A section in which the start time of the sound is different from the start time of the sound of the musical score data corresponding to the sound is specified. Here, the control unit 31 determines that the interval in which the pitch change timing of the model voice data appears earlier than the pitch change timing of the score sound data, that is, the start time of the sound included in the model voice data is the sound. For a section earlier than the sound start time of the corresponding musical score data, this section is specified as a section in which the “Tsukumi” technique is used. The control unit 31 associates the section information of the section specified in this way with identification information indicating “push”. Further, the control unit 31 calculates the time difference between the pitch change timing of the model voice data and the pitch change timing of the musical score sound data, and the calculated value is a value indicated by a 10-step numerical value as a “timing difference”. Convert to

  Conversely, the control unit 31 determines that the pitch change pronunciation timing of the model voice data is the score data based on the correspondence between the model voice data and the score sound data and the pitch calculated from the model voice data. Detects a section that appears later than the sound generation timing of the pitch, that is, a section in which the start time of the sound included in the exemplary voice data is later than the start time of the sound of the musical score sound data corresponding to the sound This section is identified as a section in which the “for” technique is used. Further, the control unit 31 calculates the time difference between the pitch change timing of the model voice data and the pitch change timing of the musical score sound data, and the calculated value is a value indicated by a 10-step numerical value as a “timing difference”. Convert to

  In addition, the control unit 31 analyzes a pattern of temporal change of the pitch calculated from the model voice data, and determines a section in which the pitch continuously fluctuates within a predetermined range above and below the center frequency. Detecting and identifying the detected section as a section in which the “vibrato” technique is used. In addition, the control unit 31 calculates a pitch fluctuation range in the detected section, and converts the calculated value into a value indicated by a numerical value of 10 levels as the degree of “depth” of this technique. Further, the control unit 31 converts the time length of the detected section into a value indicated by a numerical value of 10 steps as the degree of “length” of this technique. Further, the control unit 31 converts the pitch fluctuation speed in the detected section into a value indicated by a numerical value of 10 steps as the degree of “speed”.

  Further, the control unit 31 analyzes a pattern of temporal change in pitch calculated from the model voice data, detects a section in which the pitch continuously changes from a low pitch to a high pitch, and detects the detected section as “ It is identified as a section where the technique of “shakuri” is used. This process may be performed based on the correspondence with the musical score data. That is, the control unit 31 can detect a section in which the pitch of the exemplary voice data is continuously approaching the pitch of the musical score sound data from a low pitch based on the correspondence between the exemplary voice data and the score sound data. That's fine. Further, the control unit 31 calculates the inclination by dividing the detected amount of change in the pitch of the section by the section, and the calculated value is a value indicated by a numerical value in 10 steps as the degree of “inclination” of this technique. Convert to Further, the control unit 31 converts the detected change amount of the pitch into a value indicated by a numerical value in 10 steps as the degree of the “pitch difference”.

  In addition, the control unit 31 is a section in which the score sound data is sound based on the correspondence between the model voice data and the score sound data and the power calculated from the model voice data. A section in which the power value of the data is smaller than a predetermined threshold is detected, and the detected section is specified as a “breathing” section. Further, the control unit 31 converts the time length of the detected section into a value indicated by a numerical value of 10 steps as the degree of “length” of this technique.

Further, the control unit 31 analyzes the temporal change pattern of the spectrum calculated from the model voice data, and detects and detects a section in which the spectral characteristics are rapidly transitioning to a predetermined change state. The section is identified as the section in which the “Falset” technique is used. Here, the predetermined change state is a state in which the harmonic component of the spectrum characteristic is extremely reduced. For example, in the case of the local voice, many harmonic components are included, but in the case of a falset, the magnitude of the harmonic components becomes extremely small. In this case, the control unit 31 may also refer to whether or not the pitch has changed significantly upward. The falset is sometimes used even when uttering the same pitch as the local voice, but is generally a technique used when uttering a high pitch that cannot be uttered by the local voice. Therefore, the “false set” may be detected only when the pitch of the model voice data is equal to or higher than a predetermined pitch. In addition, the male voice and female voice generally have different pitch ranges using the falset, so gender detection is performed based on the voice range of the model voice data and the formant detected from the model voice data. A pitch region may be set.
Moreover, the control part 31 makes the information which shows the pitch (pitch) of the detected area the information of the aspect of this technique.

  In addition, the control unit 31 detects a section in which the mode of change of the spectral characteristics changes variously in a short time, and identifies the detected section as a section in which the “fist” technique is used. In the case of “fist”, this is a technique for adding a taste that changes the voice color and utterance method in a short section, so that the spectral characteristics change variously in the section where this technique is used. . Further, the control unit 31 converts the time length of the detected section into a value indicated by a numerical value of 10 steps as the degree of “length” of this technique.

As described above, the control unit 31 detects the section in which the technique is used and the mode of the technique from the model voice data, and sets the section information indicating the detected section as the type information indicating the technique and the mode of the technique. Feature extraction data associated with the information indicating is generated (step S6).
FIG. 7 is a diagram illustrating an example of the content of the feature extraction data generated in step S6. As shown in the figure, this data is configured by associating items of “technique type”, “section”, and “mode” with each other.

  Next, the control unit 31 averages each parameter of the generated feature extraction data to generate the feature data block shown in FIG. 5, and associates the generated feature data block with the model ID received from the karaoke apparatus 2. And stored in the feature data storage area 32d (step S7). Specifically, for example, the control unit 31 calculates an average value of each value of “depth”, “speed”, and “length” of the “vibrato” technique, and “feature data” of the characteristic data of the “vibrato” technique. The calculated average value is set for each parameter of “depth”, “speed”, and “length”. In addition, the total number of sections in which the “vibrato” technique is used is counted, the number is converted into a value indicated by a numerical value in 10 steps, and the converted value is set as a parameter of “frequency”. This conversion process may be performed, for example, by comparing a predetermined value with the counted total number, or an average value of the total number for each technique calculated from a plurality of exemplary feature extraction data and You may make it carry out by comparing. Similarly for other techniques, the average value and total number of each parameter are calculated, and the calculated value is set for each parameter of the feature data.

  By performing a series of processes shown in FIG. 6 for a plurality of model persons, the feature data storage area of the server device 3 indicates feature data indicating a portion where a technique for advancing the singing voices of the plurality of model persons is used. Is stored in association with the model ID.

<B-2: Guide voice data processing operation>
Next, the processing operation of the guide voice data will be described.
In the sequence diagram shown in FIG. 8, the practitioner operates the operation unit 24 of the karaoke device 2 to perform an operation of selecting a song ID of a song to be sung and a modeler ID of a favorite modeler, thereby reproducing the song. Instruct. The operation unit 24 outputs a signal corresponding to the operated content to the control unit 21, and the control unit 21 selects the song ID assigned to the song according to the signal supplied from the operation unit 24, and The model ID assigned to the person is selected (step S11). Next, the control unit 21 transmits the selected model ID and music ID to the server device 3 through the communication unit 28 (step S12).

The server device 3 receives the model ID and the song ID from the karaoke device 2. The control part 31 of the server apparatus 3 receives the input of model person ID and music ID (step S13). When the input of the model ID and the music ID is received, the control unit 31 reads the guide voice data corresponding to the music ID for which the input has been received from the guide voice data storage area 32a and corresponds to the model ID that has received the input. The feature data included in the feature data block to be read is read from the feature data storage area 32d, and a portion corresponding to the read feature data is processed based on the read guide data (step S14). More specifically, the control unit 31 sets each guide voice data corresponding to the music ID at a location indicated by the time information stored in the item “timing” of the technique insertion location designation data corresponding to the music ID. Apply processing corresponding to the technique. At this time, the control unit 31 determines whether or not the value of the “frequency” parameter for each technique included in the feature data satisfies the “condition” for each technique included in the technique location designation data. If the condition is satisfied, a processing corresponding to the technique is applied to the location indicated by “timing”. On the other hand, when the condition is not satisfied, the control unit 31 does not perform the processing.
Specifically, the control unit 31 sets the guide voice data in the location indicated by “timing” in the guide voice data corresponding to the music ID according to the parameters such as the depth, speed, and length of the feature data. Convert and process the waveform. In the shackle portion, the pitch conversion processing is similarly performed to reflect the steepness of the feature data and the start pitch, and in the case of the falset, the spectrum conversion is processed from the pitch of the part that changes to the falset. Similarly for other techniques, the control unit 31 processes the guide voice data using the feature data.

  Since the feature data corresponding to the modeler ID is data representing the features of the singing voice of the modeler favorite by the practitioner, the control unit 31 processes the guide voice data using the feature data, so that the practitioner Data indicating the singing voice imitating the singing voice of the favorite model person is generated. Specifically, for example, when the modeler always applies vibrato at the end of the phrase, data representing the singing voice to which vibrato is applied at the timing specified by the technique location specifying data is processed by the control unit 31. Generated by. Alternatively, when the model uses a falset at a certain pitch or higher, data representing a singing voice that becomes a falset at the same pitch or higher is generated by the processing of the control unit 31.

  The control unit 31 outputs the guide voice data by transmitting the processed guide voice data in a data format reproducible by the karaoke apparatus 2 (step S15). The control unit 21 of the karaoke apparatus 2 reproduces the received guide voice data (step S16). That is, the control unit 21 supplies the guide voice data to the voice processing unit 26, and the voice processing unit 26 converts the guide voice data into an analog signal and emits sound from the speaker 27. Thereby, the practitioner can listen to the singing voice imitating the singing voice of the singer that he / she wants to imitate, and can improve his / her singing by using it as a model.

  As described above, in the present embodiment, the control unit 31 processes the guide voice data corresponding to the selected music ID using the feature data corresponding to the selected model ID. Thus, the singing voice imitating the singing voice of the model person that the practitioner wants to imitate can be provided as a model to the practitioner. In other words, even if a modeler who wants to imitate a practitioner does not have the song as a song and has never sung the song, as if the modeler sang the song The trainer can hear the singing voice. The practitioner listens to the singing as a model and uses the way of singing as a model, so the practitioner's motivation is likely to improve.

<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, data representing a singing voice sung by a certain singer is used as the guide voice data. Instead of this, guide vocal data may be generated from accompaniment data using a singing synthesizer or the like, and the generated guide vocal data may be used as guide voice data. In this case, if the data indicating the characteristics of the voice of the model person is included in the feature data as the characteristic data for each model person, the guide voice data more similar to the voice of the model person can be created. it can.

(2) In the embodiment described above, the feature data is generated from the singing voice of the model person. In addition to this, the singing voice of the practitioner is recorded, and the voice data generated by recording is subjected to the same processing to generate feature data. The comparison result may be notified to the practitioner. In this case, specifically, for example, the practitioner's singing voice is picked up by the microphone 25 of the karaoke device 2, and the voice processing unit 26 generates and generates the practitioner voice data representing the practicing singing voice. The control unit 21 calculates the pitch, timing, spectrum, and power from the trainee voice data, and generates the trainer feature data from the calculation result. Then, the karaoke device 2 or the server device 3 compares the feature data of the practitioner and the feature data of the model person for each parameter, and the control unit 21 of the karaoke device 2 displays the comparison result on the display unit 23. The comparison result is notified by outputting it as a voice message.
In this way, the practitioner will know how close or similar his singing technique (how to use the technique) is to the exemplar's singing technique by referring to the notification result. Can do.

(3) In the above-described embodiment, feature data of a plurality of models are extracted using one reference song. The model voice data for extracting the feature data does not need to be voice data when the same reference song is sung, but a plurality of model people sing different songs, and feature data from each song voice May be extracted.

(4) In the above-described embodiment, technique insertion location designation data for specifying a portion for processing the guide voice data is stored in advance in the technique insertion location designation data storage area 32c of the server device 3. . Instead of this, the control unit 31 of the server device 3 may generate data for specifying a portion for processing the guide voice data. Specifically, for example, the control unit 31 generates feature extraction data from a plurality of model voice data for a certain piece of music, takes statistics for each technique for the generated plurality of feature extraction data, and for each technique, You may make it produce | generate the data which show the area where the technique is used in the ratio more than a predetermined threshold value as data for specifying the part which processes guide audio | voice data.
In the above-described embodiment, the technique is inserted into the guide voice data at the timing (part) indicated by the technique insertion location designation data (the guide voice data is processed). The method for specifying the portion for processing the guide data, that is, the portion corresponding to the feature data is not limited to the specification based on the technique insertion location designation data. For example, the control unit 31 of the server device 3 performs the musical score sound data and the guide sound. You may make it identify based on data. Specifically, for example, it may be specified on the basis of a predetermined algorithm, such as specifying that a vibrato technique is inserted for a sound of half notes or more.

In the above-described embodiment, whether to insert a technique is determined according to the “condition” included in the technique insertion location designation data. However, the determination method is not limited to this. The location of the timing based on a predetermined algorithm, for example, when the control unit 31 of the server device 3 makes a determination by randomly extracting the number of insertion locations (timing) according to the frequency of each technique. It may be determined whether or not a technique is to be inserted.
Alternatively, instead of determining whether or not to insert a technique, the technique may be inserted into all of the parts indicated by the technique insertion location designation data.

(5) In the embodiment described above, the case where the guide voice data representing the singing voice is processed has been described. However, the present invention is not limited to this, and the guide voice data representing the performance sound of the musical instrument may be processed. In this case, instead of the singing voice of a certain singer described above, guide voice data representing the performance sound of the performer is used, and feature data indicating the characteristics of a specific part in the progression of the musical instrument performance sound is used. In the accompaniment / lyric data storage area 22a, musical score sound data defined as performance sounds in the musical score is stored. Based on these data, the control unit 31 of the server device 3 processes the guide voice data through the same processing as described above.

(6) In the above-described embodiment, the feature data is generated by the control unit 31 of the server device 3. Instead, the feature data is generated by the control unit 21 of the karaoke device 2. May be. Alternatively, the control unit 31 of the server device 3 may prompt the input of feature data, and the feature data prepared in advance may be input.
Moreover, in embodiment mentioned above, the server apparatus 3 received the model ID and music ID by receiving model ID and music ID from the karaoke apparatus 2. Instead, the server device 3 is provided with an operation unit, and the operator inputs the model ID and the music ID by operating the operation unit, and the control unit 31 of the server device 3 controls the model ID and music. You may make it receive the input with ID. Or you may make it the control part 31 receive the input of model ID and music ID via interfaces, such as USB (Universal Serial Bus). In short, the control unit 31 may accept input of the model ID and the music ID.

(7) In the above-described embodiment, data indicating techniques such as “vibrato”, “push”, and “for” is used as the feature data. However, it is necessary to use all the techniques used in the above-described embodiment. However, any one of them may be used, or a plurality of them may be used. Further, the characteristic data may be data indicating characteristics of a part where a singing technique or performance technique other than those shown in the above-described embodiment is used. For example, it may be data indicating the characteristics of a portion where a so-called harmonics technique for playing overtones with a stringed instrument or the like is used.
Further, the feature data is not limited to data indicating the feature of the part where the technique is used, and may be, for example, a part where singing is started. In short, it may be data indicating the characteristics of a specific part in the progress of the singing voice or the musical instrument performance sound.

  Further, in the above-described embodiment, the model ID assigned to the model person is used as the identification information for identifying the feature data block. However, the identification information for identifying the feature data block is not limited to this. It may be information. In short, a plurality of feature data blocks including one or a plurality of feature data may be stored, and a plurality of identification information for identifying each feature data block may be stored.

(8) Although the guide voice data and the model voice data are data in the WAVE format or MP3 format, the data format is not limited to this, and any data representing singing voice or performance sound can be used. Data in such a format may be used.

(9) In the above-described embodiment, the music practice support system 1 in which the karaoke device 2 and the server device 3 are connected via the network 4 realizes all the functions according to the above-described embodiment. On the other hand, three or more devices connected via a 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.

(10) The program executed by the control unit 21 of the karaoke device 2 or the control unit 31 of the server device 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, a CD ( It can be provided in a state of being stored in a recording medium such as a Compact Disk (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 the whole structure of a music practice assistance system. It is a block diagram which shows the structure of a karaoke apparatus. It is a block diagram which shows the structure of a server apparatus. It is a figure which shows an example of the technique insertion location designation | designated data memorize | stored by the server apparatus. It is a figure which shows an example of the characteristic data block memorize | stored by the server apparatus. It is a sequence diagram which shows operation | movement of embodiment. It is a figure which shows an example of the feature extraction data. It is a sequence diagram which shows operation | movement of embodiment.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Music practice support system 2, 2a, 2b, 2c ... Karaoke apparatus, 3 ... Server apparatus, 4 ... Network, 21 ... Control part, 22 ... Memory | storage part, 23 ... Display part, 24 ... Operation part, 25 ... Microphone , 26 ... audio processing unit, 27 ... speaker, 28 ... communication unit, 31 ... control unit, 32 ... storage unit, 33 ... communication unit.

Claims (5)

A feature that stores a plurality of feature data blocks including one or a plurality of feature data indicating features of a specific part in the progress of a singing voice or a musical instrument performance sound, and stores a plurality of identification information for identifying each of the feature data blocks. Data storage means;
A guide voice data storage means for storing a plurality of sets of song identification information for identifying a song and guide voice data representing the singing voice or performance sound of the song in association with each other;
Input receiving means for receiving input of the identification information and the music identification information;
Guide voice data reading means for reading guide voice data corresponding to the music identification information received by the input receiving means from the guide voice data storage means;
Feature data reading means for reading out feature data included in the feature data block corresponding to the identification information received by the input receiving means from the feature data storage means;
Guide voice data processing means for processing a portion corresponding to the feature data read by the feature data reading means with respect to the guide voice data read by the guide voice data reading means, based on the feature data;
An output means for outputting the guide voice data processed by the guide voice data processing means.   The music practice support apparatus according to claim 1, wherein the specific part is a part where a singing technique or a performance technique is used.   3. The music practice support according to claim 2, wherein the specific part is a part in which at least one of a technique of vibrato, shackle, fist, falsetto, squeeze, and breathing is used. apparatus. A feature that stores a plurality of feature data blocks including one or a plurality of feature data indicating features of a specific part in the progress of a singing voice or a musical instrument performance sound, and stores a plurality of identification information for identifying each of the feature data blocks. Music practice support comprising data storage means, music identification information for identifying music, and guide voice data storage means for associating and storing a plurality of sets of guide voice data representing singing voice or performance sound of the music, and control means An apparatus control method comprising:
The control means accepting input of the identification information and the music identification information;
Reading guide voice data corresponding to the music identification information received from the guide voice data storage means;
Reading out feature data contained in a feature data block corresponding to the identification information received from the feature data storage means;
Processing the portion corresponding to the read feature data with respect to the read guide voice data based on the feature data;
And a step of outputting the processed guide voice data. A feature that stores a plurality of feature data blocks including one or a plurality of feature data indicating features of a specific part in the progress of a singing voice or a musical instrument performance sound, and stores a plurality of identification information for identifying each of the feature data blocks. A computer comprising: data storage means; and guide voice data storage means for storing a plurality of sets of song identification information for identifying a song and guide voice data representing the singing voice or performance sound of the song in association with each other.
An input receiving function for receiving input of the identification information and the music identification information;
A guide voice data reading function for reading guide voice data corresponding to the music identification information received by the input receiving function from the guide voice data storage unit;
A feature data reading function for reading out feature data included in the feature data block corresponding to the identification information received by the input receiving function from the feature data storage unit;
A guide voice data processing function for processing a portion corresponding to the feature data read by the feature data reading means with respect to the guide voice data read by the guide voice data reading function, based on the feature data;
A program for realizing an output function for outputting guide voice data processed by the guide voice data processing function.

Images