JP4839967B2 - Instruction device and program - Google Patents

Description

The present invention relates to a guidance instrumentation 置及 beauty program.

In the guidance of singing and musical instrument performance, guidance is given in which a model singer (or player) shows a model and sings (or performs) in a similar manner. For example, in Japanese Patent Laid-Open No. 2004-260, the user performance display and the model performance display are displayed according to the respective note numbers and velocities in order to convey the difference between the user performance and the model performance to the user in an easy-to-understand manner. There has been proposed a method of displaying a figure in a position corresponding to each note number and generation timing.
JP 2002-91290 A

By the way, skilled singers like singers rarely sing songs mechanically along the score. To express emotion in the song. Many people who practice singing have a desire to sing by imitating such intentional timing shifts and singing techniques.
However, in the conventional singing instruction apparatus, such an intentional singing method of the singer could not be easily communicated to the practitioner. The same applies to the performance of musical instruments.
The present invention has been made under the background described above, and it is an object of the present invention to provide a technique that can easily convey a singer's singing method (or a player's playing method) to a practitioner.

A teaching device according to a preferred aspect of the present invention includes: first storage means for storing musical score sound data representing pronunciation timings of a plurality of phonemes whose pronunciation timings are connected in time series; and model sound data representing a model sound. The second storage means for storing and the model sound data stored by the second storage means are divided for each phoneme, and the association is made to associate the musical score sound data stored by the first storage means with each phoneme unit. Based on the association result by the means and the association means, the pronunciation timing of each phoneme represented by the musical score sound data is converted into the pronunciation timing of the phoneme represented by the exemplary sound data to generate processed musical score sound data Processed musical score data generating means; and output means for outputting the musical score data and the processed musical score data generated by the processed musical score data generating means.
In this aspect, the output means may display on the display means the pronunciation period of the phoneme represented by the musical score sound data and the pronunciation period of the phoneme represented by the processed musical score data corresponding to the same time axis. .
In this aspect, the sound analysis data generating means for generating sound analysis data indicating at least one of the pitch, spectrum and power of the model sound data from the model sound data, and the sound analysis data generation means Analyzes the temporal change pattern of the generated sound analysis data, determines whether or not the analysis result corresponds to a predetermined pattern, and if so, identifies the section corresponding to the pattern A technique section specifying means for specifying as a section in which the technique is used, and the output means corresponds to a section specified by the technique section specifying means among the phoneme pronunciation sections represented by the processed musical score data. The display mode of the portion to be displayed may be displayed on the display means different from the display mode of the other sections.
In this aspect, the sound analysis data generating means generates sound analysis data indicating a pitch from the model sound data, and the technique section specifying means is a pitch indicated by the sound analysis data generated by the sound analysis data generating means. Analyzing the temporal change pattern of the sound, identifying a section that continuously changes from a low pitch to a high pitch, and the output means includes the technique section of the phoneme pronunciation section represented by the processed musical score data. You may display on the said display means the display mode of the part corresponding to the area specified by the specific means as a display mode showing the pitch change of the said area.

  According to the present invention, the singing method of the singer (or the performing method of the performer) can be communicated to the practitioner in an easy-to-understand manner.

Next, the best mode for carrying out the present invention will be described.
<A: Configuration>
FIG. 1 is a block diagram showing a hardware configuration of a karaoke apparatus 1 according to an embodiment of the present invention. The karaoke apparatus 1 has a karaoke function for reproducing karaoke accompaniment and also functions as a singing instruction apparatus for instructing a practitioner to sing. In the figure, 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. Control each part of the karaoke apparatus 1. The storage unit 14 is a large-capacity storage unit such as a hard disk, and includes an accompaniment data storage area 14a, a musical score data storage area 14b, an exemplary sound data storage area 14c, and an exemplary technique data storage area 14d. ing. The display unit 15 is, for example, a liquid crystal display, and displays various screens such as a menu screen for operating the karaoke device 1 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 such as a numeric keypad, an up / down key, and a performance start key, and outputs an operation signal corresponding to the pressed key to the CPU 11. The microphone 17 collects the voice uttered by the practitioner and outputs a voice signal (analog data). The audio processing unit 18 converts an audio signal (analog data) output from the microphone 17 into digital data and outputs the digital data to the CPU 11. The speaker 19 emits sound with an intensity corresponding to the audio signal output from the audio processing unit 18.

In the accompaniment data storage area 14a of the storage unit 14, accompaniment data in which performance sounds of various musical instruments that accompany the music are recorded as the music progresses is stored in association with the music ID assigned to the music. Yes. 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.
In the musical score data storage area 14b, musical score data representing the pronunciation timing of a plurality of phonemes (each word constituting the lyrics) whose pronunciation timing is continuous in time series is stored. The data format of the musical score data is a data format such as MIDI format.

  In the model sound data storage area 14c, for example, voice data in the WAVE format or MP3 (MPEG1 Audio Layer-3) format, etc., which is a singing voice (hereinafter referred to as a model) sung by the singer in accordance with the accompaniment represented by the accompaniment data , Voice data representing model voice) (hereinafter, model voice data) is stored.

In the exemplary technique data storage area 14d, data indicating the type and timing of the singing technique used for the exemplary singing voice represented by the exemplary sound data stored in the exemplary sound data storage area 14c (hereinafter referred to as "exemplary technique"). Data ") is stored.
FIG. 2 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 “technique type” 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 sound 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 item of “technical type”, for example, identification information for identifying a technique of singing such as “vibrato”, “shakuri”, “fist”, “farset”, “tsukkomi”, “for”, “breathing” is stored. The “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 adding decorative and undulating tunes. “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.

<B: Operation>
<B-1: Operation example 1>
Next, the operation of the karaoke apparatus 1 will be described with reference to the flowchart shown in FIG.
The practitioner operates the operation unit 16 of the karaoke apparatus 1 to perform an operation of selecting a song to be sung. The operation unit 16 outputs an operation signal corresponding to the operated content to the CPU 11, and the CPU 11 selects music according to the operation signal output from the operation unit 16. The CPU 11 reads out the model sound data corresponding to the selected music piece from the model sound data storage area 14c, detects the pitch and spectrum from the read out model sound data in frame units of a predetermined time length, and indicates the detected pitch and spectrum. Sound analysis data is generated (step S1). FFT (Fast Fourier Transform) is used for spectrum detection. Subsequently, based on the spectrum of the model sound data and the score sound data, the CPU 11 determines the correspondence (corresponding part) between the phoneme (word) included in the model sound data and the phoneme (word) included in the score sound data. Obtained (step S2). That is, the CPU 11 divides the model sound data into phonemes, and associates the model sound data and the score sound data in units of phonemes.

There is a possibility that the sounding timing of each phoneme in the model voice data and the sounding timing of each phoneme in the musical score sound data are shifted in time. Specifically, for example, when an exemplary singer sings by intentionally shifting the start and end of singing, the exemplary voice and the score sound are shifted forward and backward in time. In this way, even if the model voice and the score sound are shifted forward and backward in time, the pronunciation of the lyrics (phonemes) in the model sound data is performed using voice recognition technology so that they can be associated with each other. Identify timing. Note that the sound generation timing of each phoneme in the model sound data may be manually cut in advance and stored in association with the phoneme and the sound generation timing.
In FIG. 4, a waveform G <b> 1 is a waveform indicating the sound represented by the model sound data, and solid lines G <b> 21 to G <b> 28 indicate the pitch and sounding timing for each phoneme represented by the musical score sound data. In the figure, for example, it can be seen that the pronunciation start timing and the pronunciation end timing of the phoneme corresponding to the word “ta” are shifted forward and backward in time between the model voice and the score sound. In this way, even if the sound generation timing of the model voice is shifted from the sound generation timing of the score sound, by performing voice recognition, the time axis of one sound data is expanded or contracted to match the time axis of the other sound data, It is possible to associate phonemes having the same position on the time axis adjusted by the expansion and contraction.

Next, the CPU 11 converts the sound generation timing of each phoneme represented by the musical score sound data to the sound generation timing of the phoneme represented by the model sound data based on the association result of Step S2, and generates processed musical score sound data (Step S11). S3). Next, the CPU 11 outputs the musical score sound data and the processed musical score sound data generated in step S3 to the display unit 15, thereby generating the phoneme sounding interval represented by the musical score sound data and the phoneme sounding interval represented by the processed musical score sound data. Are displayed on the display unit 15 in correspondence with the same time axis (step S4).
FIG. 5 is a diagram illustrating an example of a screen displayed on the display unit 15 in step S4. In the figure, solid lines G21 to G28 (hereinafter referred to as “solid line G2”) indicate the phoneme sounding sections represented by the musical score data, and solid lines G31 to G38 (hereinafter referred to as “solid line G3”) are processed. It shows the phoneme pronunciation interval represented by the musical score data. In addition, in the example shown in FIG. 5, although the waveform G1 of model sound data is also shown for reference, this waveform G1 may not be displayed.
In the solid line G2 and the solid line G3, the vertical axis indicates the pitch height, and the horizontal axis indicates the time. The CPU 11 displays the solid line G2 and the solid line G on the display unit 15 in association with the same time axis. That is, the solid line G2 and the solid line G3 represent the pitches of the phonemes and the sounding timings (sounding start timing and sounding end timing) included in each of the musical score sound and the processed musical score sound. Further, the solid line G2 and the solid line G3 are displayed by being separated at a separation position for each phoneme.

  When the model singer uses the so-called “push” technique that makes the singing start earlier than the original timing or the so-called “for” technique that makes the singing later than the original timing, practice Even if the person sees the solid line G2 representing the musical score, he cannot grasp the location where the model singer has shifted the pronunciation timing. Further, even if the waveform of the model voice as shown in the waveform G1 is viewed, it is often difficult for the user to grasp the sound generation timing from the waveform. On the other hand, in the present embodiment, since the phoneme pronunciation timing indicated by the solid line G3 is the phoneme pronunciation timing of the model voice, the practitioner can view the model voice by looking at the screen displayed on the display unit 15. It becomes easy to grasp the pronunciation timing. Furthermore, by displaying the practitioner's pitch curve in an overlapping manner, it is possible to express the delay in pronunciation timing with respect to the model voice.

<B-2: Operation example 2>
Next, a second operation example of this embodiment will be described below with reference to the flowchart shown in FIG. In the flowchart shown in FIG. 6, the processing shown in steps S1 and S2 is the same as that shown in FIG. 3, and the description thereof is omitted here.
When the correspondence relationship between the model sound data and the musical score sound data is obtained (step S2), the CPU 11 then specifies a section in which the technique of “shaking” is used based on the pitch detected from the model sound data. . Then, the CPU 11 stores the section information of the specified section in the model technique data storage area 14d of the storage unit 14 in association with the type information indicating the singing technique (step S13). More specifically, the CPU 11 analyzes a pattern of temporal change in pitch calculated from the model sound data, detects a section where the pitch continuously changes from a low pitch to a high pitch, and detects the detected section as “ Identifies the section in which the singing technique of “shakuri” is used. At this time, the CPU 11 stores the pitch data indicating the start pitch and the end pitch of the identified section in the exemplary technique data storage area 14d in association with the type information indicating “shak” and the section information of the identified section. To do.
A specific example will be described with reference to FIG. In FIG. 7, a curve G4 is a graph representing the pitch of the model voice. When the CPU 11 executes the process of step S13, the sections k1, k2, and k3 of the curve G4 are specified as the sections in which the “shaking” technique is used.
This process may be performed based on the correspondence with the musical score data. That is, the CPU 11 may detect a section in which the pitch of the model sound data continuously approaches the pitch of the score sound data from a low pitch based on the correspondence relationship between the model sound data and the already created G3.

  Next, the CPU 11 converts the sound generation timing of each phoneme represented by the musical score sound data to the sound generation timing of the phoneme represented by the model sound data based on the association result of Step S2, and generates processed musical score sound data (Step S11). S14). This process is the same as the process in step S3 in FIG.

Next, the CPU 11 outputs the musical score sound data and the processed musical score sound data generated in step S14 to the display unit 15 so that the pronunciation interval of each phoneme represented by the musical score sound data and the pronunciation interval of the phoneme represented by the modified musical score data. Are displayed on the display unit 15 in correspondence with the same time axis. (Step S15). At this time, the CPU 11 refers to the model technique data stored in the model technique data storage area 14d of the storage unit 14 by the process of step S14, and among the pronunciation intervals of the phonemes represented by the processed musical score sound data, The display mode of the portion corresponding to the section in which the technique is used is displayed on the display unit 15 in a display mode that represents the pitch change of the section.
FIG. 8 is a diagram illustrating an example of a screen displayed on the display unit 15 in step S15. In the figure, G31 to G38 are created in step S14, and dotted lines G31A to G38A represent processed musical score data. The CPU 11 displays the portions corresponding to the sections k1, k2, and k3 where the “shackle” technique is used in the dotted lines G31A to G38A in a shape indicating the pitch change of the section. Specifically, for example, in the section k1, the pitch change is shown from the pitch p1 at the start time to the pitch p2 at the end time.
By viewing the screen displayed on the display unit 15, it becomes easy for the practitioner to understand at what timing the “sucking” technique is used.

<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 second operation example, the CPU 11 extracts a section in which the “shrimp” technique is used from the model sound data. The technique of extraction is not limited to “shrimp”, and may be, for example, “vibrato”, “fist”, “farset”, “breathing”, “staccato”, “crescendo”, and the like.
Specifically, the CPU 11 analyzes a pattern of temporal change of the pitch calculated from the model sound data, and determines 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 is a section in which the musical score sound data is sound based on the correspondence between the exemplary sound data and the musical score sound data and the power calculated from the exemplary musical sound data, and the power value of the exemplary musical sound data is the same. A section smaller than a predetermined threshold is detected, and the detected section is specified as a "breathing" section.
In addition, the CPU 11 analyzes the temporal change pattern of the spectrum calculated from the model sound 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, in the case of a local voice, many harmonic components are included, but when a false set is used, the magnitude of the harmonic components becomes extremely small. 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. .
Further, the CPU 11 may detect a section in which the power detected from the model sound data appears strong only for a short period of time as a staccato. Alternatively, a section in which the power data value continuously increases and decreases (decrease) may be detected as crescendo (decrescendo).
In short, the CPU 11 analyzes a pattern of temporal change in pitch, power, and spectrum indicated by sound analysis data generated from the model sound data, and determines whether or not the analysis result corresponds to a predetermined pattern. When it determines and respond | corresponds, what is necessary is just to identify the area corresponding to the said pattern as an area where the specific song technique is used.

Even in the case of detecting a singing technique other than “shakuri”, the CPU 11 displays the display mode of the portion corresponding to the section specified as using the technique among the phoneme pronunciation sections represented by the processed musical score data. What is necessary is just to display on the display part 15 by making it the display mode showing the pitch change of the said area.
Specifically, for example, as illustrated in FIG. 9, the CPU 11 may represent the section with a wavy line in the section k12 in which the “vibrato” technique is used. Further, in the section k11 in which the “crescendo” technique is used, the CPU 11 may display so that the thickness of the line representing the section gradually increases.

(2) In the above-described embodiment, it is displayed by being separated at the separation position for each phoneme. Instead of this, the breathing interval may be expressed by the break position of each line representing the sounding interval.

(3) In the above-described embodiment, the phoneme sounding section represented by the musical score sound data and the phoneme sounding section represented by the processed music sound data are represented by horizontally extending line figures. The graphic representing the phoneme pronunciation interval of the musical score sound data and the processed musical score sound data is not limited to the above-described line shape, but may be, for example, a rectangular shape, or a plurality of circular shapes connected together. It may be a figure, and what is important is that the phoneme pronunciation interval represented by the processed musical score sound data and the phoneme pronunciation interval represented by the processed musical score sound data are displayed corresponding to the same time axis. It may be anything.

(4) In the above-described embodiment, as the sound analysis data, data indicating the pitch and spectrum detected from the model sound data is used, and a section in which the technique of “shaking” is used is extracted from the sound analysis data. did. The sound analysis data is not limited to the pitch, but any data that can identify the section in which the singing technique to be extracted is used. For example, when extracting the singing technique of “Sharukuri” or “Vibrato”, the model sound data Data indicating the pitch may be used as the sound analysis data. For example, when the “crescendo” technique is extracted, data indicating the power may be used as the sound analysis data. In short, the sound analysis data may be data indicating at least one of the pitch, spectrum, and power of the model voice data.

(5) In the above-described embodiment, data indicating both the pronunciation start timing and the pronunciation end timing of the phoneme is used as the data indicating the sound generation timing. Good.

(6) In the above-described embodiment, the CPU 11 extracts the technique from the model sound data and generates the model technique data. Instead of this, the model technique data may be stored in advance. In this case, the CPU 11 does not need to perform processing for generating model technique data from the model sound data.

(7) In the above-described embodiment, the model sound data is stored in the model sound data storage area 14c, and the CPU 11 of the karaoke apparatus 1 reads the model sound data from the storage unit 14, but instead, The model sound data may be received via a communication network. Also, the model sound data may be input via an interface such as USB (Universal Serial Bus).

(8) In the above-described embodiment, the karaoke apparatus 1 realizes all the functions according to the present embodiment. On the other hand, two or more devices connected via a communication network may share the above functions, and a system including the plurality of devices may realize the karaoke device 1 of the embodiment.

(9) In the embodiment described above, the CPU 11 outputs the processed musical score sound data to the display unit 15. Alternatively, the processed musical score data may be output by being transmitted to a predetermined server device via a communication network. Alternatively, the processed musical score data may be output via an interface such as a USB.

(10) Programs executed by the CPU 11 of the karaoke apparatus 1 in the above-described embodiment are magnetic tape, magnetic disk, flexible disk, optical recording medium, magneto-optical recording medium, CD (Compact Disk) -ROM, DVD (Digital Versatile). Disk) or a storage medium such as a RAM. It is also possible to download to the karaoke apparatus 1 via a network such as the Internet.

(11) In the embodiment described above, the model sound data representing the model singing voice and the score sound data are associated with each other, and the score sound data is processed based on the correspondence result. The model sound data in the present invention is not limited to sound data representing a singing sound, and can also be applied to sound data representing a performance sound of a musical instrument. Also in this case, the CPU of the karaoke apparatus associates the sound data representing the performance sound of the musical instrument with the score sound data, and processes the score sound data based on the correspondence result. That is, the model sound data may be voice data representing a human singing voice or voice data representing a performance sound of a musical instrument.

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 model technique data. It is a flowchart which shows the flow of the process which a karaoke apparatus performs. It is a figure for demonstrating matching with model sound data and musical score sound data. It is a figure which shows an example of the screen displayed on a display part. It is a flowchart which shows the flow of the process which a karaoke apparatus performs. It is a figure for demonstrating the detection process of the area where the technique is used. It is a figure which shows an example of the screen displayed on a display part. It is a figure which shows an example of the screen displayed on a display part.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 ... Karaoke apparatus, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ... Memory | storage part, 15 ... Display part, 16 ... Operation part, 17 ... Microphone, 18 ... Audio | voice processing part, 19 ... Speaker.

Claims (10)

First storage means for storing musical score sound data representing the sound generation timing of a plurality of phonemes whose sound generation timing is continuous in time series;
Second storage means for storing exemplary sound data representing an exemplary sound;
An association unit that divides the model sound data stored in the second storage unit for each phoneme, and associates the musical score data stored in the first storage unit with each phoneme;
Based on the association result by the association means, the modified musical score sound that generates the processed musical score sound data by converting the pronunciation timing of each phoneme represented by the musical score sound data into the pronunciation timing of the phoneme represented by the exemplary sound data Data generation means;
An instruction device comprising: output means for outputting the musical score data and the processed musical score data generated by the processed musical score data generation means. First storage means for storing musical score sound data representing the sound generation timing of a plurality of phonemes whose sound generation timing is continuous in time series;
Second storage means for storing exemplary sound data representing an exemplary sound;
An association unit that divides the model sound data stored in the second storage unit for each phoneme, and associates the musical score data stored in the first storage unit with each phoneme;
Based on the association result by the association means, the modified musical score sound that generates the processed musical score sound data by converting the pronunciation timing of each phoneme represented by the musical score sound data into the pronunciation timing of the phoneme represented by the exemplary sound data Data generation means;
Finger ShirubeSo location, characterized in that it comprises an output means for output the machining music sound data generated by the processing score sound data generating means. The output means displays the pronunciation period of the phoneme represented by the musical score sound data and the pronunciation period of the phoneme represented by the processed musical score sound data on the display means in association with the same time axis. The instruction apparatus according to 1. Sound analysis data generating means for generating sound analysis data indicating at least one of pitch, spectrum and power of the model sound data from the model sound data;
Analyze the temporal change pattern of the sound analysis data generated by the sound analysis data generation means, determine whether this analysis result corresponds to a predetermined pattern, and if it corresponds, A technique section specifying means for specifying a section corresponding to the pattern as a section in which a specific technique is used, and
The output means is configured to change a display mode of a portion corresponding to a section specified by the technique section specifying means out of a phoneme pronunciation section represented by the processed musical score sound data from a display mode of other sections. It displays on a display means. The instruction | indication apparatus of Claim 3 characterized by the above-mentioned. The sound analysis data generation means generates sound analysis data indicating a pitch from the model sound data,
The technique section specifying unit analyzes a pattern of temporal change in pitch indicated by the sound analysis data generated by the sound analysis data generation unit, and specifies a section that continuously changes from a low pitch to a high pitch. ,
The output means sets a display mode of a portion corresponding to a section specified by the technique section specifying means in a phoneme pronunciation section represented by the processed musical score sound data to a display mode indicating a pitch change of the section. It displays on a display means. The instruction | indication apparatus of Claim 4 characterized by the above-mentioned. A computer comprising first storage means for storing musical score sound data representing the pronunciation timings of a plurality of phonemes whose pronunciation timings are arranged in time series, and second storage means for storing exemplary sound data representing an exemplary sound ,
An association function that divides the model sound data stored in the second storage unit into phonemes, and associates the musical score data stored in the first storage unit with phoneme units;
Based on the association result by the association function, the modified musical score sound that generates the processed musical score sound data by converting the pronunciation timing of each phoneme represented by the musical score sound data into the pronunciation timing of the phoneme represented by the exemplary sound data Data generation function,
An output function for outputting the musical score data and the processed musical score data generated by the processed musical score data generation function. A computer comprising first storage means for storing musical score sound data representing the pronunciation timings of a plurality of phonemes whose pronunciation timings are arranged in time series, and second storage means for storing exemplary sound data representing an exemplary sound ,
An association function that divides the model sound data stored in the second storage unit into phonemes, and associates the musical score data stored in the first storage unit with phoneme units;
Based on the association result by the association function, the modified musical score sound that generates the processed musical score sound data by converting the pronunciation timing of each phoneme represented by the musical score sound data into the pronunciation timing of the phoneme represented by the exemplary sound data Data generation function,
An output function for outputting the processed musical score data generated by the processed musical score data generation function. The output function is characterized in that the phoneme pronunciation interval represented by the musical score sound data and the phoneme pronunciation interval represented by the processed musical score data are displayed on the display unit in correspondence with the same time axis. 6. The program according to 6. On the computer,
A sound analysis data generation function for generating sound analysis data indicating at least one of pitch, spectrum and power of the model sound data from the model sound data;
Analyzing the temporal change pattern of the sound analysis data generated by the sound analysis data generation function, it is determined whether or not the analysis result corresponds to a predetermined pattern. A technique section specifying function for specifying a section corresponding to the pattern as a section in which a specific technique is used, and
In the output function, the display mode of the portion corresponding to the section specified by the technique section specifying function in the phoneme pronunciation section represented by the processed musical score data is different from the display mode of the other sections. The program according to claim 8, wherein the program is displayed on a means. The sound analysis data generation function generates sound analysis data indicating a pitch from the model sound data,
The technique section specifying function analyzes a pattern of a temporal change in pitch indicated by the sound analysis data generated by the sound analysis data generation function, specifies a section that continuously changes from a low pitch to a high pitch,
The output function among the pre-Symbol processed music sound phoneme pronunciation interval data representing a display mode of the portion corresponding to the section specified by the techniques section identifying feature, in the display mode representative of a pitch variation of the section It displays on the said display means. The program of Claim 9 characterized by the above-mentioned.

Images