JP5834727B2 - Performance evaluation apparatus, program, and performance evaluation method - Google Patents

Description

  The present invention relates to a performance evaluation apparatus, a program, and a performance evaluation method for evaluating performance of music.

  Conventionally, in response to a performance of a performer, performance data that is information based on MIDI (Musical Instrument Digital Interface) is stored, and the performance data is compared with model data that is information based on MIDI stored in advance. A performance evaluation apparatus that performs correct / incorrect determination is known (see, for example, Patent Document 1).

  In such a performance evaluation apparatus, performance of a performer can be evaluated by comparing performance data, which is information based on MIDI, with model data, which is information based on MIDI, and making a correct / incorrect determination.

JP 2010-134207 A

However, in the conventional performance evaluation apparatus including the technique described in Patent Document 1, since the correctness is determined by comparing the information based on MIDI, it is limited to the performance evaluation by the electronic musical instrument that can output the information based on MIDI. It was.
That is, in the conventional performance evaluation apparatus, it has not been possible to evaluate performances using natural musical instruments that cannot output information based on MIDI.

  The present invention has been made in view of such a situation, and an object of the present invention is to make it possible to evaluate the performance of a natural musical instrument by evaluating the performance based not only on information based on MIDI but also on sound waveform data. And

In order to achieve the above object, a performance evaluation apparatus according to an aspect of the present invention includes:
Based on the evaluation reference waveform data generated by the rendition of the music as a reference of evaluation, represents one axis the time in the region in which the other axis the height of the frequency, the intensity of each frequency in the luminance value of the pixel Evaluation standard data creating means for creating the image data as evaluation standard data,
Based on the evaluation target waveform data generated by playing the musical composition to be evaluated, the one axis time in height as the regions of the frequency other axis, the intensity of each frequency in the luminance value of the pixel Evaluation object data creating means for creating the represented image data as evaluation object data;
An evaluation unit that calculates an evaluation value based on a result of comparison between the evaluation reference data created by the evaluation reference data creation unit and the evaluation target data created by the evaluation target data creation unit;
Is provided.

  According to the present invention, the performance can be evaluated based on not only the information based on MIDI but also the waveform data of the sound, so that the performance of a natural musical instrument can also be evaluated.

It is a figure explaining the outline | summary of the process which evaluates the performance in the performance evaluation apparatus which concerns on embodiment of this invention. It is a block diagram which shows the structure of the hardware of the performance evaluation apparatus which concerns on embodiment of this invention. It is a flowchart explaining the flow of the evaluation reference (teacher) image data creation process which CPU of the performance evaluation apparatus which concerns on this embodiment performs. It is a flowchart explaining the flow of the evaluation object (student) image data creation process which CPU of the performance evaluation apparatus concerning this embodiment performs. It is a flowchart explaining the flow of the data evaluation process which CPU of the performance evaluation apparatus which concerns on this embodiment performs. It is a figure explaining evaluation standard (teacher) image data. It is a figure which shows the evaluation object (student) image data. It is a flowchart explaining the flow of the evaluation value graphing process which CPU of the performance evaluation apparatus which concerns on this embodiment performs.

Hereinafter, a performance evaluation apparatus according to an embodiment of the present invention will be described with reference to the drawings.
First, in order to facilitate understanding of the present embodiment, an outline of a performance evaluation apparatus according to the present embodiment will be described.
FIG. 1 is a diagram for explaining an outline of processing for evaluating a performance in the performance evaluation apparatus according to the embodiment of the present invention.
The performance evaluation apparatus evaluates the performance by creating evaluation data for the performance of a known music piece.
In step S1, the performance evaluation apparatus performs the evaluation standard (teacher) score data D1 for each measure of the music, which becomes an evaluation standard (hereinafter also referred to as a teacher), using the software sound source, and evaluates for each measure (teacher). Waveform data D10 is created.
Here, in the present embodiment, “musical score data” is SMF (Standard MIDI File) data, for example, a chip sound source such as an electronic musical instrument, or a software sound source that is synthesized and generated by a CPU (Central Processing Unit) of a computer. It is data that can be played by a MIDI sound source such as.
In the present embodiment, the “waveform data” is data indicating the frequency of the played sound at predetermined intervals, for example, as shown in (a).

In step S2, the performance evaluation apparatus analyzes the frequency of the evaluation reference (teacher) waveform data D10 for each measure by fast Fourier transform (FFT (Fast Fourier Transform)), and the parameters on the frequency axis and the parameters on the time axis. The image data D11 for evaluation criteria (teacher) for each measure displayed in the sonogram is created (hereinafter also referred to as evaluation criteria (teacher) image data as evaluation criteria data).
Here, in this embodiment, “sonagram display” means, for example, as shown in (b), in which the horizontal axis is time, and the vertical axis is the frequency of the frequency of the played sound. Is the image data indicating the intensity of the sound by the luminance value of the pixel. In this embodiment, fast Fourier transform (FFT) is used in order to obtain the image data of “sonagram display”. However, the present invention is not limited to this, and other methods such as wavelet transform may be used. Good.

  In step S3, the performance evaluation apparatus analyzes the frequency of the evaluation target (student) waveform data D20, which is the evaluation target (hereinafter also referred to as a student), by fast Fourier transform (FFT), and displays the evaluation target (student) ) Image data D21 (hereinafter also referred to as evaluation object (student) image data as evaluation object data).

  In step S4, the performance evaluation apparatus generates evaluation data D30 based on the comparison result between the evaluation standard (teacher) image data D11 for each measure and the evaluation target (student) image data D21.

FIG. 2 is a block diagram showing a hardware configuration of the performance evaluation apparatus 1 according to the embodiment of the present invention.
In FIG. 2, the performance evaluation apparatus 1 includes a CPU 11, a ROM (Read Only Memory) 12, a RAM (Random Access Memory) 13, a bus 14, an input / output interface 15, an input unit 16, and an output unit 17. A storage unit 18, a MIDI interface unit 19, and a drive 20.

  The CPU 11 executes various processes according to a program recorded in the ROM 12 or a program loaded from the storage unit 18 to the RAM 13. Specifically, the CPU 11 executes an evaluation reference (teacher) image data creation process, an evaluation target (student) image data creation process, a data evaluation process, an evaluation value graphing process, and the like. In addition, the CPU 11 can synthesize sounds constituting the music based on the SMF data. The RAM 13 appropriately stores data necessary for the CPU 11 to execute various processes.

  The CPU 11, ROM 12, and RAM 13 are connected to each other via a bus 14. An input / output interface 15 is also connected to the bus 14. An input unit 16, an output unit 17, a storage unit 18, a MIDI interface unit 19, and a drive 20 are connected to the input / output interface 15.

  The input unit 16 includes a pointing device such as a mouse and a keyboard for character input, and outputs input signals from these to the CPU 11. When the performance evaluation apparatus 1 is configured as an electronic piano, for example, the input unit 16 includes a MIDI keyboard, and includes a keyboard and switches for inputting various information. When the key is pressed, the input unit 16 outputs to the CPU 11 a key number for identifying the key and information indicating the key pressing strength (hereinafter referred to as “velocity”). Or various information input by the user is output to the CPU 11.

The output unit 17 includes a display, a speaker, a D / A conversion circuit, and the like, and outputs images and sounds.
The storage unit 18 is composed of a hard disk or a DRAM (Dynamic Random Access Memory) and the like, and various programs for controlling the performance evaluation apparatus 1, evaluation criteria (teacher) score data D1, evaluation criteria as shown in FIG. (Teacher) Waveform data D10, evaluation reference (teacher) image data D11, evaluation object (student) waveform data D20, evaluation object (student) image data D21, and the like are stored.

  The MIDI interface unit 19 is an interface that connects the sound source 41 that generates musical sounds and the performance evaluation apparatus 1. The sound source 41 outputs a musical sound based on the SMF data.

  A removable medium 31 made of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately attached to the drive 20. The program read from the removable medium 31 by the drive 20 is installed in the storage unit 18 as necessary. The removable medium 31 can also store various data stored in the storage unit 18 in the same manner as the storage unit 18.

Next, an evaluation reference (teacher) image data creation process executed by the CPU 11 of the performance evaluation apparatus 1 according to the present embodiment will be described with reference to FIG.
FIG. 3 is a flowchart for explaining the flow of an evaluation reference (teacher) image data creation process executed by the CPU 11 of the performance evaluation apparatus 1 according to the present embodiment.
In step S21, the CPU 11 reads the evaluation standard (teacher) score data from the storage unit 18, and divides the read evaluation standard (teacher) score data for each measure of the music.

In step S22, the CPU 11 synthesizes and plays the sounds constituting the music based on the evaluation standard (teacher) score data for each measure divided in step S21, and creates evaluation standard (teacher) waveform data for each measure.
In step S23, the CPU 11 analyzes the frequency of the evaluation criterion (teacher) waveform data for each measure created in step S22 by fast Fourier transform (FFT), and evaluates (teacher) image data for each measure displayed in the sonogram. Create As described above, the CPU 11 that executes the processes of step S22 and step S23 generates the parameters on the frequency axis and the parameters on the time axis based on the evaluation reference waveform data that is generated by playing the music and is the reference for evaluation. It functions as an evaluation standard data creating means for creating evaluation standard data consisting of combinations. In addition, the CPU 11 that executes the processes of step S22 and step S23 functions as an evaluation standard data creating unit that creates evaluation standard data for each measure of the music.
In step S24, the CPU 11 stores the evaluation reference (teacher) image data created in step S23 in the storage unit 18 for each measure.

Next, an evaluation object (student) image data creation process executed by the CPU 11 of the performance evaluation apparatus 1 according to the present embodiment will be described with reference to FIG.
FIG. 4 is a flowchart for explaining the flow of the evaluation object (student) image data creation process executed by the CPU 11 of the performance evaluation apparatus 1 according to the present embodiment.
The user (student) operates the input unit 16 to specify a measure for which performance evaluation is desired.
In step S31, the CPU 11 accepts designation of a measure to be evaluated based on an operation of the input unit 16 by a user (student).
In this embodiment, the designation of a measure can be accepted for each measure, such as the Nth measure (N is an integer), or from the Nth measure to the N + nth (n is an integer), It is also possible to accept the specification of consecutive measures.

  In step S32, the CPU 11 acquires evaluation target (student) waveform data. When the input unit 16 includes a MIDI keyboard, the evaluation target (student) waveform data acquired in this step can be acquired by digitally recording the user's performance using the MIDI keyboard. Further, the evaluation target (student) waveform data acquired in this step can be acquired from the storage unit 18 or the removable medium 31 as evaluation target (student) waveform data in which the performance of the user's natural musical instrument is digitally recorded in advance. .

In step S33, the CPU 11 analyzes the frequency of the evaluation target (student) waveform data acquired in step S32 by fast Fourier transform (FFT), and creates evaluation target (student) image data to be displayed as a sonogram. As described above, the CPU 11 that executes the processes of step S32 and step S33 generates the parameters on the frequency axis and the parameters on the time axis based on the evaluation target waveform data that is generated by playing the music and is the object of evaluation. It functions as an evaluation target data creation means for creating evaluation target data consisting of a combination.
In step S <b> 34, the CPU 11 stores the evaluation target (student) image data created in step S <b> 33 in the storage unit 18.

Next, with reference to FIG. 5, the data evaluation process which CPU11 of the performance evaluation apparatus 1 which concerns on this embodiment performs is demonstrated.
FIG. 5 is a flowchart for explaining the flow of data evaluation processing executed by the CPU 11 of the performance evaluation apparatus 1 according to this embodiment.
In step S <b> 41, the CPU 11 reads out the evaluation target (student) image data stored in step S <b> 34 from the storage unit 18.
In step S <b> 42, the CPU 11 reads out from the storage unit 18 the evaluation criterion (teacher) image data of the measure received in step S <b> 31 among the evaluation criterion (teacher) image data for each measure stored in step S <b> 24. In this step, the CPU 11 reads the evaluation reference (teacher) image data from the storage unit 18 one measure at a time in the music progression order when the measure for which the designation has been received in step S31 is a plurality of consecutive measures.

In step S43, the CPU 11 compares the evaluation target (student) image data with the evaluation reference (teacher) image data, and calculates the similarity for each measure.
FIG. 6 is a diagram for explaining evaluation reference (teacher) image data.
In FIG. 6, evaluation standard (teacher) image data D11 corresponding to the musical score is shown below the musical score. In the present embodiment, the evaluation reference (teacher) image data is stored in the storage unit 18 one measure N at a time.
FIG. 7 is a diagram showing evaluation target (student) image data.
FIG. 7 shows, for example, evaluation target (student) image data D21 for one measure.
In step S43, the CPU 11 specifically associates the evaluation reference (teacher) image data D11 with the evaluation target (student) image data D21, and based on the difference in the luminance values of the pixels at the corresponding positions, the degree of similarity Is calculated. In the present embodiment, the “similarity” increases as the difference in luminance value decreases, indicating that both images are similar. That is, the higher the similarity is, the closer the performance of the user (student) is to the performance of the evaluation standard (teacher).

  It should be noted that the musical instruments and sound sources to be played are different between the performance to be evaluated (teacher) and the performance to be evaluated (student). For this reason, for example, the evaluation reference (teacher) image data D11 shown in FIG. 6 shows overtones in which patterns of the same shape appear at substantially equal intervals in the vertical axis direction. On the other hand, the evaluation object (student) image data D21 shown in FIG. Therefore, the evaluation reference (teacher) image data D11 and the evaluation target (student) image data D21 do not completely match.

  In step S44, the CPU 11 determines whether the similarity is calculated for the last measure in step S43 among the measures received in step S31, and determines that the similarity is calculated for the last measure. Moves the process to step S45, and returns to step S42 if it is determined that the similarity is not calculated for the last measure.

In step S45, the CPU 11 determines whether or not the maximum similarity among the similarities calculated in step S43 is equal to or greater than a predetermined value, and if it is determined that the maximum similarity is equal to or greater than a predetermined value, the step is performed. The process moves to S46, and if it is determined that the maximum similarity is not equal to or greater than the predetermined value, this process ends.
For example, when the user operates a MIDI keyboard without playing music, the degree of similarity is small. Also, the degree of similarity between the evaluation target (student) image data and the evaluation reference (teacher) image data of the specified measure when the measure other than the measure specified by the user is played is reduced. Here, in the present embodiment, the “predetermined value” can be an arbitrary value, but an operation of a MIDI keyboard or the like that is presumed not to play a musical piece or a performance of an unspecified measure is performed. Appropriate values for excluding evaluation are desirable.

  In step S <b> 46, the CPU 11 uses the maximum similarity among the similarities calculated in step S <b> 43 as an evaluation value, and stores the evaluation value and the measure number for which the evaluation value is calculated in the storage unit 18. In the present embodiment, the “measure number” specifies a predetermined measure in a music piece. For example, the bar number of the first bar of the music piece is “1”, and “1 + n” (n is the order of the music progression). (Integer).

  As described above, the CPU 11 that executes the processes of step S43 and step S46 uses the comparison result between the evaluation reference data created by the evaluation reference data creation unit and the evaluation target data created by the evaluation target data creation unit. It functions as an evaluation means for calculating an evaluation value based on the evaluation value. Further, the CPU 11 that executes the processes of step S43 and step S46 functions as an evaluation unit that calculates the similarity between the evaluation reference data and the evaluation target data and uses the similarity as an evaluation value. Further, the CPU 11 that executes the processing of step S43 and step S46 compares the evaluation reference data of the continuous measures with the evaluation target data, calculates the similarity, and uses the similarity as an evaluation value. Function as. Further, the CPU 11 that executes the processing of step S43 to step S46 compares the evaluation reference data with the evaluation target data for each measure, calculates the similarity, and calculates the measure having the similarity equal to or less than a predetermined value. It functions as an evaluation means with the similarity as an evaluation value.

Next, an evaluation value graphing process executed by the CPU 11 of the performance evaluation apparatus 1 according to the present embodiment will be described with reference to FIG.
FIG. 8 is a flowchart for explaining the flow of the evaluation value graphing process executed by the CPU 11 of the performance evaluation apparatus 1 according to this embodiment.
In step S <b> 51, the CPU 11 reads the evaluation value and the measure number for which the evaluation value is calculated from the storage unit 18.

  In step S52, the CPU 11 determines whether or not the measure number read in step S51 indicates the measure for which the designation is accepted in step S31. If it is determined that the measure number indicates the measure for which the designation has been accepted, step 11 is performed. If the process proceeds to S53 and it is determined that the specified measure is not indicated, this process is terminated.

  In step S53, the CPU 11 determines whether or not the evaluation value read in step S51 is the first evaluation value for the measure indicated by the measure number read in step S51, and determines that it is the first evaluation value. If so, the process proceeds to step S54. If it is determined that the evaluation value is not the first evaluation value, the process proceeds to step S55. Specifically, in step S53, the CPU 11 refers to the storage unit 18 and determines whether or not an evaluation base value to be described later is stored for the measure indicated by the measure number.

  In step S54, the CPU 11 stores the evaluation value read in step S51 in the storage unit 18 as the evaluation base value of the measure indicated by the measure number read in step S51.

  In step S55, the CPU 11 reads the evaluation base value of the measure indicated by the measure number read in step S51 from the storage unit 18, and calculates a relative value that is the difference between the evaluation base value and the evaluation value read in step S51. .

  Thus, CPU11 which performs the process of step S51 thru | or step S55 uses the evaluation value calculated by the evaluation means about the predetermined music as an evaluation base value, and the evaluation value calculated after the evaluation base value is calculated And a relative value calculating means for calculating a relative value between the evaluation base value and the evaluation base value.

  In step S56, the CPU 11 creates image data in which the relative value calculated in step S55 is graphed, and displays the graphed image data on the display unit included in the performance evaluation device 1 or an external display unit. Perform display control. In the present embodiment, “image data in which relative values are graphed” is, for example, a bar graph or a line if the difference between the evaluation base value that is an evaluation of a past performance and the evaluation value that is an evaluation of the current performance can be displayed. This is image data for showing various forms of graph images such as graphs. As described above, the CPU 11 that executes the process of step S56 functions as a display control unit that controls display of an image indicating the relative value calculated by the relative value calculation unit.

As described above, the performance evaluation apparatus 1 according to the present embodiment includes the CPU 11.
CPU11 which performs processing of Step S22 and Step S23 of this embodiment generates a parameter on a frequency axis, and a parameter on a time axis based on evaluation standard waveform data which is generated by the performance of a music and becomes a standard of evaluation. It functions as an evaluation standard data creating means for creating evaluation standard (teacher) image data which is evaluation standard data composed of combinations.
The CPU 11 that executes the processing of step S32 and step S33 is an evaluation composed of a combination of a parameter on the frequency axis and a parameter on the time axis, based on the evaluation target waveform data that is generated by the performance of the music and is the evaluation target. It functions as an evaluation target data creation means for creating evaluation target (student) image data that is target data.
The CPU 11 that executes the processes of step S43 and step S46 includes the evaluation reference (teacher) image data created by the evaluation reference data creation means and the evaluation target (student) image data created by the evaluation target data creation means. It functions as an evaluation means for calculating an evaluation value based on the comparison result.

Thereby, the evaluation reference waveform data generated by the performance of the music is converted into the evaluation reference (teacher) image data, the evaluation target waveform data generated by the performance of the music is converted into the evaluation target (student) image data, and the evaluation is performed. The reference (teacher) image data and the evaluation target (student) image data are compared, and an evaluation value is calculated. That is, the evaluation value can be calculated by converting the waveform data of the sound due to the performance into image data and comparing the image data.
Therefore, the performance can be evaluated based on not only the information based on MIDI but also the waveform data of the sound, so that the performance of a natural musical instrument can also be evaluated.

In addition, the CPU 11 that executes the processing of step S43 and step S46 of the present embodiment compares the evaluation reference (teacher) image data of the continuous bar with the evaluation target (student) image data, and calculates the similarity. Thus, it functions as an evaluation means using the similarity as an evaluation value.
Accordingly, the performance can be evaluated based on the similarity between the evaluation reference (teacher) image data and the evaluation target (student) image data.

In addition, the CPU 11 that executes the processing from step S51 to step S55 of the present embodiment is calculated after the evaluation base value is calculated with the evaluation value calculated by the evaluation unit as the evaluation base value for a predetermined music piece. It functions as a relative value calculation means for calculating a relative value between the evaluation value and the evaluation base value.
The CPU 11 that executes the process of step S56 functions as a display control unit that controls display of an image indicating the relative value calculated by the relative value calculation unit.
Thereby, by controlling the display of an image that shows the difference between the evaluation base value that is an evaluation with respect to the past performance and the evaluation value that is an evaluation with respect to the current performance, for example, as the progress of the performance technique, Can support performance practice.

In addition, the CPU 11 that executes the processes of step S22 and step S23 of the present embodiment functions as an evaluation reference data creation unit that creates evaluation reference (teacher) image data for each measure of the music.
The CPU 11 that executes the processing from step S43 to step S46 calculates the similarity by comparing the evaluation reference (teacher) image data and the evaluation target (student) image data for each measure, and the similarity is equal to or less than a predetermined value. This measure is excluded from the evaluation target and functions as an evaluation means having the similarity as an evaluation value.
As a result, measures whose similarity is equal to or less than a predetermined value can be excluded from evaluation. For example, when the user specifies a measure to be evaluated, or when a measure other than the specified measure is played. In addition, the similarity calculated by operating the musical instrument that is presumed not to play music can be excluded from the evaluation target and ignored.
Therefore, for example, it is possible to support the user's practice only for a specific measure and to evaluate only the operation of the musical instrument for the purpose of performance.

In addition, the CPU 11 that executes the processing of step S43 and step S46 of the present embodiment compares the evaluation reference (teacher) image data of the continuous bar with the evaluation target (student) image data, and calculates the similarity. Thus, it functions as an evaluation means using the similarity as an evaluation value.
Thereby, since the performance of a continuous bar can be evaluated, the user's practice about a specific continuous bar can be supported, for example.

  In addition, this invention is not limited to the above-mentioned embodiment, The deformation | transformation in the range which can achieve the objective of this invention, improvement, etc. are included in this invention.

  For example, in the above-described embodiment, the evaluation reference (teacher) waveform data is created by reading the evaluation reference (teacher) score data from the storage unit 18 and synthesizing and playing the sounds constituting the music. For example, the evaluation standard (teacher) waveform data itself may be stored in the storage unit 18 or the removable medium 31 and evaluated using the evaluation standard (teacher) waveform data. Further, the evaluation reference (teacher) waveform data may be created directly from a performance by a person who becomes the evaluation reference (for example, a teacher).

  In the above-described embodiment, the evaluation base value is the first evaluation value for a predetermined measure. However, the evaluation base value is not limited to this, and any timing, for example, a timing designated by the user or every predetermined number of times (for example, 10 The evaluation value for each time may be the evaluation base value.

  In the above-described embodiment, a general electronic device having an information processing function can be employed as the performance evaluation device 1. Specifically, for example, the performance evaluation apparatus 1 can be realized by a notebook personal computer, a desktop personal computer, a portable information terminal, a mobile phone, a portable game machine, or the like.

The series of processes described above can be executed by hardware or can be executed by software.
Each means may be constituted by hardware alone, software alone, or a combination thereof.

When a series of processing is executed by software, a program constituting the software is installed on a computer or the like from a network or a recording medium.
The computer may be a computer incorporated in dedicated hardware. The computer may be a computer capable of executing various functions by installing various programs, for example, a general-purpose personal computer.

  The recording medium including such a program is not only constituted by the removable medium 31 of FIG. 2 distributed separately from the apparatus main body in order to provide the program to the user, but also in a state of being incorporated in the apparatus main body in advance. It is comprised with the recording medium etc. which are provided in. The removable medium 31 is composed of, for example, a magnetic disk (including a floppy disk), an optical disk, a magneto-optical disk, or the like. The optical disk is composed of, for example, a CD-ROM (Compact Disk-Read Only Memory), a DVD (Digital Versatile Disk), or the like. The magneto-optical disk is configured by an MD (Mini-Disk) or the like. In addition, the recording medium provided to the user in a state of being incorporated in advance in the apparatus main body includes, for example, the ROM 12 in FIG. 2 in which the program is recorded, the hard disk included in the storage unit 18 in FIG.

  In the present specification, the step of describing the program recorded on the recording medium is not limited to the processing performed in time series along the order, but is not necessarily performed in time series, either in parallel or individually. The process to be executed is also included.

  As mentioned above, although embodiment of this invention was described, this embodiment is only an illustration and does not limit the technical scope of this invention. The present invention can take other various embodiments, and various modifications such as omission and replacement can be made without departing from the gist of the present invention. These embodiments and modifications thereof are included in the scope and gist of the invention described in this specification and the like, and are included in the invention described in the claims and the equivalent scope thereof.

The invention described in the scope of claims at the beginning of the filing of the present application will be appended.
[Appendix 1]
A performance evaluation device for evaluating the performance of music,
Evaluation standard data creating means for creating evaluation standard data consisting of a combination of a parameter on the frequency axis and a parameter on the time axis based on evaluation standard waveform data that is generated by the performance of the music and serves as a standard for evaluation;
Evaluation target data creating means for creating evaluation target data consisting of a combination of a parameter on the frequency axis and a parameter on the time axis, based on the evaluation target waveform data to be generated and evaluated by the performance of the music;
An evaluation unit that calculates an evaluation value based on a result of comparison between the evaluation reference data created by the evaluation reference data creation unit and the evaluation target data created by the evaluation target data creation unit;
A performance evaluation apparatus comprising:
[Appendix 2]
The performance evaluation apparatus according to claim 1, wherein the evaluation unit calculates a similarity between the evaluation reference data and the evaluation target data, and uses the similarity as an evaluation value.
[Appendix 3]
For the predetermined music piece, the evaluation value calculated by the evaluation means is used as an evaluation base value, and a relative value between the evaluation value calculated after the evaluation base value is calculated and the evaluation base value is calculated. A relative value calculating means;
The performance evaluation apparatus according to appendix 1 or 2, comprising display control means for controlling display of an image indicating the relative value calculated by the relative value calculation means.
[Appendix 4]
The evaluation standard data creating means creates the evaluation standard data for each measure of the music,
The evaluation means compares the evaluation reference data with the evaluation object data for each measure, calculates the similarity, and excludes the measure with the similarity less than or equal to a predetermined value from the evaluation target. The performance evaluation apparatus according to attachment 2, wherein the similarity is an evaluation value.
[Appendix 5]
The performance evaluation apparatus according to claim 4, wherein the evaluation unit compares the evaluation reference data of the continuous measures with the evaluation target data, calculates the similarity, and uses the similarity as an evaluation value. .
[Appendix 6]
A computer that controls a performance evaluation device that evaluates the performance of a song,
Evaluation reference data creating means for creating evaluation reference data comprising a combination of a parameter on the frequency axis and a parameter on the time axis, based on the evaluation reference waveform data that is generated by the performance of the music and serves as a reference for evaluation,
Evaluation target data creating means for creating evaluation target data consisting of a combination of a parameter on the frequency axis and a parameter on the time axis, based on the evaluation target waveform data that is generated by the performance of the music and is the target of evaluation
An evaluation means for calculating an evaluation value based on a result of comparison between the evaluation reference data created by the evaluation reference data creation means and the evaluation target data created by the evaluation target data creation means;
A program characterized by functioning as
[Appendix 7]
A performance evaluation method executed by a performance evaluation device that evaluates the performance of a song,
An evaluation reference data creation step for creating evaluation reference data consisting of a combination of a parameter on the frequency axis and a parameter on the time axis based on the evaluation reference waveform data that is generated by the performance of the music and is a reference for evaluation;
An evaluation target data creation step for creating evaluation target data consisting of a combination of a parameter on the frequency axis and a parameter on the time axis based on the evaluation target waveform data to be generated and evaluated by the performance of the music;
An evaluation step for calculating an evaluation value based on a result of comparison between the evaluation reference data created by the evaluation reference data creation step and the evaluation target data created by the evaluation target data creation step;
The performance evaluation method characterized by including.

  DESCRIPTION OF SYMBOLS 1 ... Performance evaluation apparatus, 11 ... CPU, 12 ... ROM, 13 ... RAM, 14 ... Bus, 15 ... Input / output interface, 16 ... Input part, 17 ... Output unit, 18 ... storage unit, 19 ... MIDI interface unit, 20 ... drive, 31 ... removable media, 41 ... sound source

Claims (8)

Based on the evaluation reference waveform data generated by the rendition of the music as a reference of evaluation, represents one axis the time in the region in which the other axis the height of the frequency, the intensity of each frequency in the luminance value of the pixel Evaluation standard data creating means for creating the image data as evaluation standard data,
Based on the evaluation target waveform data generated by playing the musical composition to be evaluated, the one axis time, the other axis in height as the regions of the frequency, the luminance value of the pixel intensity of each frequency Evaluation object data creating means for creating the represented image data as evaluation object data;
An evaluation unit that calculates an evaluation value based on a result of comparison between the evaluation reference data created by the evaluation reference data creation unit and the evaluation target data created by the evaluation target data creation unit;
A performance evaluation apparatus comprising:   The performance evaluation apparatus according to claim 1, wherein the evaluation unit calculates a similarity between the evaluation reference data and the evaluation target data, and uses the similarity as an evaluation value. For the predetermined music piece, the evaluation value calculated by the evaluation means is used as an evaluation base value, and a relative value between the evaluation value calculated after the evaluation base value is calculated and the evaluation base value is calculated. A relative value calculating means;
The performance evaluation apparatus according to claim 1, further comprising display control means for controlling display of an image indicating the relative value calculated by the relative value calculation means. The evaluation standard data creating means creates the evaluation standard data for each measure of the music,
The evaluation means compares the evaluation reference data with the evaluation object data for each measure, calculates the similarity, and excludes the measure with the similarity less than or equal to a predetermined value from the evaluation target. The performance evaluation apparatus according to claim 2, wherein the similarity is an evaluation value.   5. The performance evaluation according to claim 4, wherein the evaluation means compares the evaluation reference data of the continuous measures with the evaluation target data, calculates the similarity, and uses the similarity as an evaluation value. apparatus. The performance evaluation apparatus further includes a keyboard, a MIDI interface unit for inputting SMF data,
The performance evaluation apparatus according to claim 1, further comprising: a sound source unit that outputs a musical sound based on the input key number and SMF data. A computer that controls the performance evaluation device ,
Based on the evaluation reference waveform data generated by the rendition of the music as a reference of evaluation, represents one axis the time in the region in which the other axis the height of the frequency, the intensity of each frequency in the luminance value of the pixel Evaluation standard data creating means for creating the image data as evaluation standard data,
Based on the evaluation target waveform data generated by playing the musical composition to be evaluated, the one axis time, the other axis in height as the regions of the frequency, the luminance value of the pixel intensity of each frequency Evaluation object data creation means for creating the represented image data as evaluation object data;
An evaluation means for calculating an evaluation value based on a result of comparison between the evaluation reference data created by the evaluation reference data creation means and the evaluation target data created by the evaluation target data creation means;
A program characterized by functioning as A performance evaluation method executed by the performance evaluation apparatus ,
Based on the evaluation reference waveform data generated by the rendition of the music as a reference of evaluation, represents one axis the time in the region in which the other axis the height of the frequency, the intensity of each frequency in the luminance value of the pixel An evaluation standard data creation step for creating the image data as evaluation standard data,
Based on the evaluation target waveform data generated by playing the musical composition to be evaluated, the one axis time, the other axis in height as the regions of the frequency, the luminance value of the pixel intensity of each frequency An evaluation object data creation step of creating the represented image data as evaluation object data;
An evaluation step for calculating an evaluation value based on a result of comparison between the evaluation reference data created by the evaluation reference data creation step and the evaluation target data created by the evaluation target data creation step;
The performance evaluation method characterized by including.