JP2018159900A - Performance evaluation system - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an evaluation system capable of outputting a simulation of a performance to which a high evaluation is given.SOLUTION: A system 1 includes: a plurality of evaluation parts 41, 42 each configured to evaluate with respect to a performance which includes at least one of singing or instrument play while associating with the time or segment of the performance; a storage part 60 configured to store the evaluations; and an acquisition part 204 configured to acquire a piece of effect data associated with the evaluation of performance to a terminal apparatus 20 to which an acoustic signal included in the performance is newly input from the storage part 60. The terminal apparatus 20 is configured so that, when an acoustic signal which is included in the performance is newly input, the effect associated with the effect data is given to the acoustic signal at the time or segment which is associated with the evaluation.SELECTED DRAWING: Figure 1

Description

  The present invention relates to a performance evaluation apparatus.

  As a technique for evaluating performance such as singing, for example, as a karaoke scoring technique, the pitch and volume of the singing are compared with reference data that serves as a scoring standard (example), and the higher the difference, the higher the evaluation The contents are known (see, for example, Patent Document 1).

JP 2016-29429 A

  By the way, in the above technique, the singing is objectively evaluated, but the actual skill of the singing is not determined only by whether or not it follows the example prescribed by the reference data. For example, even a song that is out of the example may be able to impress or inspire people. In such a case, although it should be high evaluation depending on a person, since such a song deviates from a model, according to the said technique, it will become low evaluation.

On the other hand, if a singing method considered to be highly evaluated can be simulated and output, high satisfaction can be obtained. Although singing has been described here, the same can be said for evaluating performance as an expression, such as playing a musical instrument.
The present invention has been made in view of such circumstances, and one of its purposes is to provide a technique for simulating and outputting a performance that has been highly evaluated.

  In order to achieve the above object, a performance evaluation apparatus according to an aspect of the present invention includes an evaluation unit that evaluates a performance including at least one of singing or playing in association with a time or a section of the performance, and the evaluation An accumulating unit that accumulates evaluations by unit according to the performance, and a provision unit that reads and provides the performance evaluation from the accumulating unit to a terminal device in which an acoustic signal included in the performance is newly input, When the acoustic signal newly included in the performance is newly input, the terminal device applies a production effect associated with the evaluation for the performance to the acoustic signal for a time or interval associated with the evaluation.

It is a block diagram which shows the structure of the system which concerns on embodiment. It is a figure for demonstrating evaluation data. It is a figure for demonstrating effect data. It is a figure which shows the structure in the case of functioning as a performance evaluation apparatus. It is a flowchart which shows performance evaluation operation | movement. It is a figure which shows the structure in the case of functioning as a performance production apparatus.

Embodiments of the present invention will be described below with reference to the drawings.
FIG. 1 is a block diagram illustrating a configuration of a system 1 according to the embodiment. In this figure, the system 1 has two functions. Specifically, the system 1 has a function as an evaluation device that evaluates performance such as singing and a function as an effect device that gives an effect to the performance.
In the system 1, the terminal device 20 is a computer, for example, and the functions of the input unit 202, the acquisition unit 204, and the effect applying unit 206 are realized by executing a predetermined application program.
For convenience of explanation, as a performance, singing by the singer 10 will be described as an example.

The input unit 202 inputs an acoustic signal when the singer 10 sings and outputs it to the network 30. On the other hand, the acquisition unit 204 acquires evaluation data via the network 30, and the effect imparting unit 206 imparts an effect according to the acquired evaluation data to the acoustic signal from the singer 10.
Note that the signal to which the effect is imparted by the effect imparting unit 206 is emitted by the speaker 208. The network 30 is typically the Internet.

In addition to the terminal device 20, evaluation units 41 and 42 and a storage unit 60 are connected to the network 30.
Among these, the evaluation part 41 is a computer operated by the operator 51 in the example of a figure. The operator 51 is a music specialist such as a teacher in a music classroom, for example, and listens to a song based on an acoustic signal supplied via the network 30 and subjectively evaluates the song. The result is input to the evaluation unit 41. The evaluation unit 42 is a computer operated by a similar operator 52. The operator 52 also actually listens to a song based on the acoustic signal supplied via the network 30, and subjectively determines the song, and inputs the evaluation result to the evaluation unit 42. You may be a member of SNS (Social Networking Service).

The upper column of FIG. 2 is an example of evaluation data created by the operator 51 inputting an evaluation result.
In the evaluation data A shown in this figure, the evaluation contents of a certain song are recorded in time series from the start point to the end point, such as evaluation (1), evaluation (2), and evaluation (3). The evaluation content here is based on the subjective judgment of the operator 51 (or 52) such as “Like”, and is specified in association with the elapsed time (or section) in the singing. .
On the other hand, the middle column of FIG. 2 is an example of evaluation data created by inputting an evaluation result input by another operator 52. The evaluation data B shown in this figure is the evaluation content for the singing of the same song, but the evaluation (5) and the evaluation (6) are associated with each other at different points.

  Although the system 1 includes two evaluation units 41 and 42, in reality, a large number of evaluation units are provided with three or more units. By providing a large number of evaluation units in this way, a large number of evaluation results can be obtained for the same single song. Even if the number of evaluation units is small, even in a configuration in which different operators input evaluation results for one song, a large number of evaluation results can be obtained.

The accumulation unit 60 accumulates evaluation data for the same single song.
As an accumulation mode, for example, evaluation data A based on the evaluation result of the operator 51 and evaluation data B based on the evaluation result of the operator 52 are arranged in the order of time series as shown in the lower column of FIG. It can be considered that the evaluation data C is arranged as described above. In such a case, a plurality of evaluation contents may overlap at the same time.

When the accumulation unit 60 accumulates evaluation data for the same song, the accumulation unit 60 creates effect data corresponding to the accumulation result. As shown in FIG. 3, the effect data is obtained by arranging effect contents corresponding to evaluation contents in a time series.
Whereas the content of the evaluation is data accompanied by subjective judgment by the operator, the content of the effect is data that objectively defines what kind of singing of the portion to which the content of evaluation is given.
For example, the storage unit 60 compares the acoustic signal of the time (section) for which the evaluation content is given with an exemplary referenceator, and creates a collection of data that defines how the difference fluctuated. To do. For this reason, when another person sings the same song at a later date, when the sound signal is given to the singing signal as an effect at the same time (section) and the sound is emitted, the evaluation is performed first. The content can be made similar to the singing method.

  On the other hand, after accumulating the evaluation data, the accumulating unit 60 reads out the effect data corresponding to the acoustic signal (song) when the acoustic signal of the same song is input to the terminal device 20, and It is supplied to the terminal device 20.

  Next, the operation of the system 1 when functioning as an evaluation device will be described first.

FIG. 4 is a diagram illustrating a configuration in the case where the system 1 functions as an evaluation apparatus, and the functions of the acquisition unit 204 and the effect imparting unit 206 in FIG. 1 have expired (the block is not used).
The singer 10 sings by inputting a song name (song number) using a panel (not shown). At this time, a cappella or karaoke performance may be accompanied. The input unit 202 outputs the acoustic signal of the song performed by the singer 10 to the network 30 in association with the song name, and the operators 51 and 52 listen to the acoustic signal and evaluate the song as follows.

FIG. 5 is a flowchart showing the evaluation operation in the evaluation unit 41 (42).
This evaluation operation is executed by, for example, a predetermined program in the evaluation unit 41 (42) which is a computer.
First, the operator 51 (52) listens to an acoustic signal and inputs evaluation contents while designating a singing point (section) (step Sa1). For example, the evaluation unit 41 (42) displays from the start point to the end point of the singing in a bar graph, and the operator 51 (52) of the singing to be evaluated as “Like” in the bar graph. Specify by touching a point (section). The evaluation unit 41 records the evaluation of the point in association with the song name. Thereby, the evaluation content is associated with one place of the point.

  Next, the evaluation unit 41 (42) determines whether or not an end of evaluation has been instructed (step Sa2). Specifically, the evaluation unit 41 (42) displays an evaluation continuation button and an evaluation end button, respectively, and determines whether or not the evaluation end button has been touched by the operator 51 (52). To do.

If the end of the evaluation is not instructed (if the determination result in step Sa is “No”), the evaluation unit 41 (42) returns to step Sa1 to prepare for the input of the next evaluation content. If the end of the evaluation is instructed (if the determination result in step Sa is “Yes”), the evaluation unit 41 (42) associates all of the input evaluation contents with each performance point and further corresponds to the song name. Then, the data is supplied to the storage unit 60 (step Sa3), and the evaluation operation is terminated.
In the storage unit 60, when the evaluation data associated with the song title is supplied from the evaluation unit 41 (42), if the evaluation data has already been recorded, as shown in the lower column of FIG. If there is no evaluation data stored and associated with the song name, the evaluation data is recorded as it is.
Thus, the evaluation data for the song is sequentially stored in the storage unit 60 for each song.

  When a predetermined condition is satisfied in a state where the evaluation data is accumulated, for example, when a predetermined number of pieces of evaluation data are accumulated, the accumulation unit 60 creates effect data corresponding to the evaluation data.

FIG. 6 is a diagram showing a configuration when the system 1 functions as a rendering device, and the functions of the input unit 202 and the evaluation units 41 and 42 in FIG. When the singer 10 inputs a song title (song number) using a panel (not shown), the song title is supplied to the storage unit 60 via the network 30. Here, the singer 10 may be the same person as the singer 10 when functioning as an evaluation device, or may be a different person.
The storage unit 60 searches for the effect data corresponding to the song title, and if there is, supplies the effect data to the acquisition unit 204 via the network 30. The acquisition unit 204 sets the effect data in the effect applying unit 206. When the acoustic signal of the singing by the singer 10 is input, the effect imparting unit 206 imparts the effect defined by the effect data to the acoustic signal for the time (section) defined by the effect data. Note that the speaker 208 emits sound based on the signal to which the effect is given.

According to the function of this effect device, when a new song is sung, the effect specified by the already created effect data is given to the song and the sound is emitted from the speaker 208. Here, the singer who newly sings does not ask whether it is a singer who created evaluation data or another person.
The case where the singer who created the evaluation data sings is a practice when, for example, the evaluation data is created, but the case where the singer newly sings is a performance.
In production, due to tension, it may not sing as well as practice. Even in such a case, since the effect of the content evaluated at the time of practice is given to the song at the time of performance, the song emitted from the speaker 208 can be made similar to the song at the time of practice.
On the other hand, when another person sings newly from the singer who created the evaluation data, the effect of the content that has already been evaluated is given to the singing by the other person. It can be made similar to a song that has been evaluated.

  In the system 1, the evaluation unit 41 (42) subjectively determines the singing by the operator 51 (52). For example, the level of applause or cheer included in the acoustic signal is greater than or equal to a threshold value. It is good also as a structure judged objectively by whether it is.

  Moreover, although it was set as the structure which inputs the acoustic signal accompanying a song to the input part 202, it is good also as a structure which inputs the sound accompanying performances, such as a guitar, a violin, a piano other than a song, as an acoustic signal. According to this configuration, when a new performance is performed, the performance sound that accompanies the performance is given to the performance sound that accompanies the performance, so that the performance sound emitted from the speaker 208 is evaluated. You can resemble the performance you are playing. Both performance sound and singing sound may be included. That is, the performance is an expression including at least one of singing or playing.

DESCRIPTION OF SYMBOLS 1 ... System, 20 ... Terminal device, 41, 42 ... Evaluation part, 60 ... Accumulation part, 202 ... Input part, 204 ... Acquisition part, 206 ... Effect provision part.

Claims (1)

For a performance that includes at least one of singing or performance, an evaluation unit that evaluates in association with the time or section of the performance,
An accumulation unit for accumulating evaluations by the evaluation unit;
An acquisition unit 204 that acquires, from a storage unit, effect data associated with an evaluation of the performance to a terminal device in which an acoustic signal included in the performance is newly input;
Comprising
When the terminal device newly receives an acoustic signal included in the performance, the terminal device performs an effect associated with the effect data on the acoustic signal for a time or interval associated with the evaluation. .

Images