JP6358018B2 - Karaoke device and program - Google Patents

Description

  The present invention relates to a karaoke apparatus and a program.

  2. Description of the Related Art Conventionally, in a karaoke apparatus, a karaoke apparatus is known that converts a voice quality of a singing voice of a song by a user into a voice quality of an original singer of the music and outputs it (see Patent Document 1). Specifically, in the karaoke apparatus described in Patent Document 1, the difference between the singing signal input by the user singing and the original signal representing the singing voice of the original singer is calculated, and the calculated difference is the original. An output signal is generated by adding to the signal. And in the karaoke apparatus described in patent document 1, the sound based on the produced | generated output signal is emitted.

Japanese Patent Laid-Open No. 08-263077

  By the way, in the karaoke apparatus described in Patent Document 1, the parameter converted into the characteristics of the original singer's singing voice is only the voice quality, and other parameters in the singing voice such as pitch, volume, and singing are not converted. For this reason, although the sound output from the karaoke apparatus described in Patent Document 1 has the voice quality of the original singer, for example, the pitch may be shifted or the volume may be low.

  That is, in the conventional karaoke apparatus, although the evaluation with respect to the audio | voice output from the said karaoke apparatus is high about a specific evaluation item, there exists a possibility that it may become low about other evaluation items other than a specific evaluation item.

In other words, the conventional karaoke apparatus has a problem that the sound output from the karaoke apparatus becomes unbalanced.
Therefore, an object of the present invention is to improve the balance in the sound output from the karaoke apparatus.

  The present invention made to achieve the above object relates to a karaoke apparatus including a voice acquisition unit, a reference acquisition unit, a feature calculation unit, a coincidence degree calculation unit, a correction unit, and an output unit.

  The voice acquisition means in the present invention acquires singing voice data representing the voice input via the microphone during the performance of the designated music piece. The designated music referred to here is a designated music among at least one music in which lyrics are assigned to at least a part of a plurality of notes composed of combinations of pitches and note values.

  The reference acquisition means acquires the evaluation reference data of the designated music from the evaluation reference data. The evaluation standard data referred to here is data representing the evaluation standard of each of a plurality of evaluation items defined as items for evaluating the singing of the music for each music.

  Furthermore, the feature calculation means in the present invention calculates a singing feature amount representing an evaluation for each evaluation item in the singing voice data, based on the singing voice data acquired by the voice acquisition means. The degree of coincidence calculation means calculates, for each evaluation item, an evaluation degree of coincidence that is a degree of coincidence between the singing feature amount calculated by the feature calculation means and the evaluation criteria represented by the evaluation reference data acquired by the reference acquisition means.

Then, the correcting means is a voice acquisition means so that the evaluation matching degree approaches the specific reference value for at least one evaluation item whose evaluation matching degree calculated by the matching degree calculation means is lower than the specified specific reference value. The singing voice data acquired in step 1 is corrected. Further, the output means outputs the singing voice data corrected by the correction means.

According to such a karaoke device, an evaluation item whose evaluation coincidence is lower than a specific reference value in the sound (ie, the singing sound of the user of the karaoke device) input through the microphone during the performance of the designated music piece ( That is, it can correct | amend so that it may become high evaluation about an evaluation item with low evaluation. On the other hand, in the karaoke apparatus of the present invention, the voice input through the microphone is not corrected for the evaluation item whose evaluation matching degree is equal to or higher than the specific reference value (that is, the evaluation item with high evaluation).

  That is, according to the karaoke apparatus of the present invention, it is possible to correct and output only the evaluation items with low evaluation in the singing voice. Therefore, according to the karaoke apparatus of the present invention, the evaluation for each evaluation item in the voice output from the karaoke apparatus can be made uniform, and the evaluation of the entire singing voice can be improved. In other words, according to the karaoke apparatus of the present invention, it is possible to improve the balance in the sound output from the karaoke apparatus.

  From the above, according to the karaoke apparatus of the present invention, the degree of satisfaction of a singer who is singing music can be improved. Furthermore, since the listener of the karaoke apparatus of the present invention can listen to a well-balanced sound, the degree of satisfaction is improved. Therefore, according to the karaoke apparatus of the present invention, the satisfaction level of both the singer and the listener can be improved.

Further, the correcting means in the present invention may correct the evaluation matching degree so as to approach the specific reference value for all evaluation items whose evaluation matching degree is lower than the specific reference value.
According to such a karaoke apparatus, a more balanced sound can be output.

  Furthermore, in the present invention, the evaluation coincidence of the highest evaluation item may be used as the specific reference value. In this case, the correction means according to the present invention may correct the evaluation items whose evaluation matching degree is lower than the specific reference value so that the evaluation matching degree approaches the specific reference value.

According to such a karaoke apparatus, other evaluation items in the singing voice data can be corrected so as to approach the evaluation item having the highest evaluation among the evaluation items.
As a result, according to the karaoke apparatus, the balance of the output voice can be further improved, and the degree of satisfaction of both the singer and the listener can be further improved.

In the karaoke apparatus of the present invention, display means may be provided. The display means in this case identifies at least one evaluation item whose evaluation coincidence calculated by the coincidence degree calculating means is lower than the specific reference value and at least one evaluation item whose evaluation coincidence is equal to or higher than the specific reference value. It may be displayed in a possible manner.

  In such a karaoke apparatus, in the singing voice output from the karaoke apparatus, an evaluation item for which correction has been performed and an evaluation item for which correction has not been performed are displayed in an identifiable manner.

As a result, the user of the karaoke apparatus can recognize the corrected evaluation item and the evaluation item that has not been corrected.
By the way, this invention may be made | formed as a program which makes a computer perform an audio | voice acquisition step, a reference | standard acquisition step, a feature calculation step, a coincidence degree calculation step, a correction | amendment step, and an output step.

  In the sound acquisition step in such a program, singing sound data representing the sound input via the microphone during the performance of the designated music is acquired. In the reference acquisition step, evaluation reference data for the designated music is acquired.

  In the feature calculation step, the singing feature amount is calculated based on the singing voice data acquired in the voice acquisition step. Further, in the coincidence degree calculating step, an evaluation coincidence degree, which is a coincidence degree between the singing feature quantity and the evaluation reference represented by the evaluation reference data, is calculated for each evaluation item.

In the correction step, the singing voice data is corrected so that the evaluation coincidence approaches the specific reference value for at least one evaluation item whose evaluation coincidence is lower than the specific reference value. In the output step, the singing voice data corrected in the correction step is output.

The present invention may be implemented as a program executed by a computer.
As described above, if the present invention is implemented as a program, it is used by loading the computer from a recording medium as necessary and starting it, or by acquiring it and starting it through a communication line as necessary. be able to. And by making a computer perform each procedure, the computer can be functioned as a karaoke apparatus described in claim 1.

  The recording medium referred to here includes, for example, a computer-readable electronic medium such as a DVD-ROM, a CD-ROM, and a hard disk.

It is a block diagram which shows schematic structure of the karaoke system provided with the karaoke apparatus to which this invention was applied. It is a flowchart which shows the process sequence of a karaoke performance process. It is a figure explaining the calculation method of the evaluation coincidence in a karaoke performance process. It is a figure which shows an example of the correction method which used sound pressure as the evaluation item in a karaoke performance process. It is a figure which shows an example of the correction method which used vibrato as the evaluation item in karaoke performance processing.

Embodiments of the present invention will be described below with reference to the drawings.
<Karaoke system>
The karaoke system 1 shown in FIG. 1 is an evaluation item that preliminarily defines voices input during the performance of the designated music while playing the music designated by the user (hereinafter referred to as “designated music”). Evaluate each singing evaluation item. And the karaoke system 1 correct | amends and outputs the audio | voice input during the performance of the designated music about the at least 1 singing evaluation item whose evaluation result is below a specific reference value. In the following, the voice input during the performance of the designated music is referred to as singing voice data.

In order to realize this, the karaoke system 1 includes an information processing server 10 and a karaoke device 30.
The information processing server 10 includes a communication unit 12, a storage unit 14, and a control unit 16.

  Among these, the communication unit 12 performs communication between the information processing server 10 and the outside via a communication network. That is, the information processing server 10 is connected to the karaoke apparatus 30 via a communication network. The communication network referred to here may be a wired communication network or a wireless communication network.

  The storage unit 14 is a known storage device configured to be able to read and write stored contents. The storage unit 14 stores at least a plurality of MIDI music pieces MD. Further, the storage unit 14 stores evaluation reference data AS that represents evaluation criteria for evaluating the singing voice data for each singing evaluation item and for each piece of music. The evaluation reference data AS is stored in the storage unit 14 in association with the MIDI music MD for each corresponding music.

  1 is an identifier for identifying the MIDI music piece MD and the evaluation reference data AS stored in the storage unit 14 of the information processing server 10, and is assigned to each music piece. This code “n” is a natural number of 1 or more.

The control unit 16 is a known control device that is configured around a known microcomputer including a ROM 18, a RAM 20, and a CPU 22. The ROM 18 stores processing programs and data that need to retain stored contents even when the power is turned off. The RAM 20 temporarily stores processing programs and data. The CPU 22 executes each process according to a processing program stored in the ROM 18 or the RAM 20.
<MIDI music>
The MIDI music MD is prepared in advance for each music and has music data and lyrics data.

  Among these, the music data is data representing the score of one music according to the well-known MIDI (Musical Instrument Digital Interface) standard. This music data has at least a music ID and a music score track representing a music score for each musical instrument used in the music.

  The musical score track defines at least the pitch (so-called note number) and the period during which the MIDI sound source outputs the performance sound (hereinafter referred to as the note length) for each performance sound output from the MIDI sound source. Has been. The note length in the score track is the performance start timing (so-called note-on timing) indicating the time from the start of the performance of the music until the output of the performance sound and the music until the output of the performance sound ends. Performance end timing (so-called note-off timing) representing the time from the start of the performance.

  That is, in the score track, one note NO is defined by the note number and the note length represented by the note-on timing and note-off timing. The musical score track functions as one musical score by arranging note NO in the order of performance.

  On the other hand, the lyrics data is data relating to the lyrics of the music, and includes lyrics telop data and lyrics output data. The lyrics telop data represents characters that constitute the lyrics of the music (hereinafter referred to as lyrics component characters). The lyrics output data is data in which a timing correspondence relationship that associates the lyrics output timing, which is the output timing of the lyrics constituent characters, with the performance of the performance data is defined.

Specifically, in the timing correspondence relationship in the present embodiment, the timing for starting the output of the lyrics telop data is associated with the timing for starting the performance of the performance data. Furthermore, in the timing correspondence relationship, the lyrics output timing of each lyrics constituent character along the time axis of the music is defined by the elapsed time from the performance start of the performance data. Thereby, each performance sound (namely, note NO) prescribed | regulated to the score track | truck and each lyric component character are matched.
<Evaluation criteria data>
The evaluation standard data AS is data representing the evaluation standard of the singing voice data for each predetermined period defined for each piece of music and for each singing evaluation item. The evaluation reference data AS may be, for example, scoring reference data defined in advance based on an exemplary singing voice that sang a song, or guide vocal itself that is an exemplary singing voice that sings a song. There may be.

  As a singing evaluation item in the present embodiment, the characteristics of the singing voice (hereinafter referred to as “singing characteristics”) and the voice quality of the singer who uttered the singing voice (hereinafter referred to as “singing voice quality”). included.

  The singing characteristics in the present embodiment include a pitch transition that represents a transition of the pitch in the singing voice, a sound pressure transition that represents a transition of the sound pressure in the singing voice, and a singing technique expressed by the singing voice. The singing technique mentioned here includes at least “vibrato”.

  Specifically, the evaluation reference data AS of the present embodiment includes model feature information that represents singing characteristics in an exemplary singing voice that sang a song, and model voice quality information that represents singing voice quality in the exemplary singing voice. ing.

  The model feature information is data representing the feature amount of the singing feature in the model singing voice. The model feature information includes pitch transition information representing transition of pitch in singing voice, sound pressure transition information representing transition of sound pressure in singing voice, and technique information representing singing technique represented by singing voice. Including. The skill information associates the type of singing technique used in the singing voice, the timing at which the singing technique is used, and the technique feature quantity representing the feature quantity of the used singing technique.

The technical feature amount (hereinafter referred to as “vibrato feature amount”) vib for “vibrato” may be calculated by the following procedure.
In the calculation procedure of the vibrato feature quantity vib, first, frequency analysis (DFT (discrete Fourier transform)) is performed on the singing voice (hereinafter referred to as a note vocal) Vo (a, i) for the note NO (i) to which the lyrics are assigned. carry out. Then, the vibrato feature amount vib is calculated according to the following equation (1).

vib (a, i) = vib_per (a, i) × vip_dep (a, i) (1)
However, vib_per (a, i) in the above equation (1) is an index representing the protruding accuracy of the spectrum peak in each note vocal Vo (a, i). This vib_per may be obtained by dividing the peak value of the frequency analysis result (that is, the amplitude spectrum) by the average value of the frequency analysis result. Further, vip_dep in the above equation (1) is a standard deviation of each note vocal Vo (a, i).

In the present embodiment, the code “a” is a code for identifying a song, and the code “i” is a code for identifying a note that constitutes the song and is assigned lyrics.
The model voice quality information is data representing the characteristic amount of the voice quality of the singer who uttered the singing voice. The feature quantity of voice quality referred to here is, for example, a mel frequency cepstrum (MFCC).

This exemplary voice quality information may be expressed for each note constituting the music, or may be expressed for each predetermined section including a plurality of notes specified for the music, or for each music. Also good.
<Karaoke equipment>
The karaoke apparatus 30 plays the designated music based on the MIDI music MD stored in the information processing server 10 and evaluates the singing voice data for each singing evaluation item. And the karaoke apparatus 30 correct | amends and outputs singing voice data so that an evaluation result may approach a specific reference value about the at least 1 singing evaluation item whose evaluation result is below a specific reference value.

  In order to realize this, the karaoke apparatus 30 includes a communication unit 32, an input reception unit 34, a music playback unit 36, a storage unit 38, an audio control unit 40, a video control unit 46, and a control unit 50. It has.

  In the communication unit 32, the karaoke apparatus 30 communicates with the outside via a communication network. The input receiving unit 34 is an input device that receives input of information and commands in accordance with external operations. Here, the input device is, for example, a key, a switch, a reception unit of a remote controller, or the like.

The music playback unit 36 performs a music performance based on the MIDI music MD downloaded from the information processing server 10. The music reproducing unit 36 is, for example, a MIDI sound source.
The voice control unit 40 is a device that controls voice input / output, and includes an output unit 42 and a microphone input unit 44. A microphone 62 is connected to the microphone input unit 44. As a result, the microphone input unit 44 acquires the sound input via the microphone 62. A speaker 60 is connected to the output unit 42. The output unit 42 outputs the sound source signal of the music reproduced by the music reproducing unit 36 and the sound source signal of the singing voice from the microphone input unit 44 to the speaker 60. The speaker 60 outputs the sound source signal output from the output unit 42 instead of sound.

  The video control unit 46 outputs a video or an image based on the video data sent from the control unit 50. The video control unit 46 is connected to a display unit 64 that displays video or images.

  The control unit 50 is configured around a known computer having at least a ROM 52, a RAM 54, and a CPU 56. The ROM 52 stores processing programs and data that need to retain stored contents even when the power is turned off. The RAM 54 temporarily stores processing programs and data. The CPU 56 executes each process according to a processing program stored in the ROM 52 or the RAM 54.

The ROM 52 of the present embodiment stores a processing program for the control unit 50 to execute karaoke performance processing. In this karaoke performance process, the designated music piece is played based on the MIDI music piece MD, the singing voice data is evaluated based on the evaluation reference data AS of the designated music piece, and the evaluation result is at least a specific reference value. This is a process of correcting and outputting the singing voice data so that the evaluation result approaches a specific reference value for one singing evaluation item.
<Karaoke performance processing>
Next, karaoke performance processing executed by the control unit 50 will be described.

This karaoke performance process is activated when a predefined activation command is input via the input receiving unit 34.
Then, when the karaoke performance process shown in FIG. 2 is started, the control unit 50 first transmits the MIDI music MD corresponding to the music specified via the input receiving unit 34 (that is, the specified music) to the information processing server. 10 from the storage unit 14 (S110). Subsequently, the control unit 50 evaluates the evaluation reference data associated with the music corresponding to the MIDI music MD acquired in S110 out of all the evaluation reference data AS stored in the storage unit 14 of the information processing server 10. AS is acquired (S120).

  Further, the control unit 50 starts playing the designated music based on the MIDI music MD acquired in S110, and displays various information including lyrics on the display unit 64 (S130). Specifically, in the performance of the designated music in S130, the control unit 50 sequentially outputs the MIDI music MD to the music playback unit 36 along the time axis. The music reproducing unit 36 that has acquired the MIDI music MD performs the music. Then, the sound source signal of the music played by the music playback unit 36 is output to the speaker 60 via the output unit 42. Then, the speaker 60 outputs the sound source signal instead of sound.

  In S <b> 130, the control unit 50 outputs image signals representing various types of information to the video control unit 46. The video control unit 46 that has acquired the image signal displays various types of information on the display unit 64 in synchronization with the performance of the designated music piece by the music reproduction unit 36. In addition, the various information displayed on the display part 64 contains the evaluation result of the singing voice signal by this karaoke performance process other than the lyrics allocated to each note NO which comprises the designated music.

  And in a karaoke performance process, the control part 50 acquires the audio | voice input via the microphone 62 and the microphone input part 44 as song audio | voice data (S140). And the control part 50 memorize | stores the singing voice data acquired in S140 in the memory | storage part 38 (S150).

  Further, in the karaoke performance process, the control unit 50 determines whether or not the designated musical piece being played is within a predetermined period defined in advance (S160). The predetermined period here is at least one period defined in advance for each piece of music as a period for evaluating the singing voice data. A plurality of predetermined periods in the present embodiment are set so as to continue along the time axis of the music.

  As a result of the determination in S160, if the timing (hereinafter referred to as “current performance timing”) of the designated musical piece currently being played is outside the predetermined period (S160: NO), the control unit 50 performs the karaoke performance processing. Is shifted to S220. In S220, the control unit 50 outputs the singing voice data acquired in S140 to the voice control unit 40 without correction. The voice control unit 40 outputs the voice represented by the singing voice data to the speaker 60 via the output unit 42. Then, the speaker 60 outputs the voice represented by the singing voice data.

Thereafter, the control unit 50 shifts the karaoke performance process to S230, which will be described in detail later.
On the other hand, as a result of the determination in S160, if the current performance timing is within the predetermined period (S160: YES), the control unit 50 shifts the karaoke performance processing to S170. In S170, the control unit 50 calculates the singing feature amount in a predetermined period based on the singing voice data stored in the storage unit 38 in S150 (S170).

  This singing feature amount is data representing the feature amount for each singing evaluation item. This singing feature amount includes singing voice feature information representing the singing feature in the singing voice data and singing voice quality information representing the voice quality of the utterer (that is, the user of the karaoke device 30) in the singing voice data.

  Among these, the singing voice feature information includes the singing pitch change representing the transition of the pitch in the singing voice data, the singing sound pressure transition representing the transition of the sound pressure in the singing voice data, and the singing expressed by the singing voice data. And singing technique information representing the technique.

In the present embodiment, the singing pitch transition may be calculated by the following procedure.
In the calculation of the singing pitch transition, the control unit 50 sets the analysis time window having a specified time length in the singing voice data so as to be continuous along the time axis, and the singing voice data in each analysis time window. Is subjected to frequency analysis (for example, DFT). Then, as a result of autocorrelating the result of frequency analysis, the strongest frequency component is set to the fundamental frequency f0, that is, the pitch in the analysis time window, and arranged along the time axis to calculate the singing pitch transition.

In the present embodiment, the singing sound pressure transition may be calculated according to the following procedure.
In the calculation of the singing sound pressure transition, the control unit 50 sets the analysis time window having the specified time length in the singing voice data so as to be continuous along the time axis. Then, the root mean square (RMS (Root Mean Square)) of the amplitude of the singing voice data in each analysis time window is set as the sound pressure in the analysis time window, and the singing sound pressure transition is arranged along the time axis. calculate.

In addition, since the technique for calculating the singing skill information in the present embodiment is the same as the procedure for calculating the vibrato feature quantity vib, detailed description thereof is omitted here.
Furthermore, in the calculation of the singing voice quality information, a mel frequency cepstrum (MFCC) is calculated based on the result of frequency analysis of the singing voice data in each analysis time window, and the mel frequency cepstrum is calculated as singing voice quality information.

  In the karaoke performance process, the control unit 50 subsequently calculates an evaluation coincidence, which is a coincidence between the singing feature amount calculated in S170 and the evaluation reference data acquired in S20, for each singing evaluation item (S180). . Specifically, in S180, the control unit 50 calculates each correlation value for each singing evaluation item between the singing feature quantity and the evaluation reference data as an evaluation matching degree. In addition, since the calculation method of a correlation value is known, detailed description here is abbreviate | omitted.

  In the karaoke performance process, the control unit 50 determines whether or not at least one evaluation coincidence among all the evaluation coincidence calculated in S180 conforms to the specified correction execution condition ( S190). In S190, the control unit 50 determines that the evaluation matching degree is suitable for the correction execution condition if the evaluation matching degree for at least one singing evaluation item is equal to or less than the specified specific reference value. . In this embodiment, all evaluation coincidence calculated for each singing evaluation item in S180, that is, evaluation coincidence of pitch transition, evaluation coincidence of sound pressure transition, evaluation coincidence of singing technique, The highest evaluation matching score among the voice quality evaluation matching scores is set as the specific reference value.

  As a result of the determination in S190, if all the evaluation coincidence calculated in S180 do not match the correction execution condition (S190: NO), the control unit 50 shifts the karaoke performance process to S220. In S220, the control unit 50 outputs the singing voice data acquired in S140 to the voice control unit 40 without correction. The voice control unit 40 outputs the voice represented by the singing voice data to the speaker 60 via the output unit 42. Then, the speaker 60 outputs the voice represented by the singing voice data.

Thereafter, the control unit 50 shifts the karaoke performance process to S230.
On the other hand, as a result of the determination in S190, if at least one evaluation coincidence among all the evaluation coincidence calculated in S180 meets the correction execution condition (S190: YES), the control unit 50 The karaoke performance process is shifted to S200. In S200, for all singing evaluation items whose evaluation coincidence is lower than the specific reference value (hereinafter referred to as “correction target item”), the control unit 50 sets the evaluation coincidence of each correction target item to the specific reference value. The singing voice data is corrected so as to approach. In addition, in this embodiment, since the highest evaluation matching degree is made into the specific reference value among all the evaluation matching degrees calculated for every singing evaluation item in S180, the evaluation corresponding to the highest evaluation matching degree is carried out. Evaluation items other than the items are correction target items.

  In S190 and S200 in the present embodiment, for example, as shown in FIG. 3, the degree of coincidence for each singing evaluation item between the guide vocal and the singing voice data is minimized for each minimum evaluation period that is shorter than a predetermined period. Calculated as unit match. Then, based on the minimum unit coincidence in each of the minimum evaluation periods, the sum of the minimum unit coincidence in the minimum evaluation period equal to or more than the prescribed number is calculated as the evaluation coincidence (that is, the score). The singing voice data is corrected so that the evaluation matching degree of each correction target item matches the specific reference value with the singing evaluation item other than the singing evaluation item having the highest evaluation matching degree as the correction target item.

  As specific methods for correcting the singing voice data, a correction method (see FIG. 4) using the sound pressure transition as a singing evaluation item and a correction method (see FIG. 5) using vibrato as a singing evaluation item will be described.

  First, as a precondition of the correction method in which the sound pressure transition shown in FIG. 4 is the correction target item, the singing evaluation item regarding the sound pressure transition is, for example, according to the class of the sound pressure difference between the singing sound pressure transition and the model sound pressure transition. Assume that the evaluation coincidence is classified (ie, scored). FIG. 4 shows the case where the highest evaluation matching score (that is, the specific reference value) is “α point” and the evaluation matching score regarding the singing sound pressure transition is “β point (α> β)”. . In S <b> 200 in this case, the control unit 50 changes the sound pressure in the singing voice so that the sound pressure difference between the corrected singing sound pressure change and the exemplary sound pressure change becomes a sound pressure difference corresponding to the “α point” class. (In the example shown in FIG. 4, it is amplified to “−y [dB]”).

  Further, as a precondition of the correction method in which the vibrato shown in FIG. 5 is the correction target item, the singing evaluation items related to vibrato are, for example, the vibrato amplitude that is the difference between the maximum amplitude and the minimum amplitude in the fluctuation of the vibrato amplitude, and vibrato Assume that the evaluation coincidence is classified (that is, scored) according to the vibrato speed, which is the speed of frequency fluctuations at. FIG. 5 shows a case where the highest evaluation evaluation coincidence is “α point” and the vibrato evaluation coincidence is “β point (α> β)”. In S200 in this case, the control unit 50 assigns vibrato in the singing voice so that the set of vibrato amplitude and vibrato speed becomes a set of vibrato amplitude and vibrato speed corresponding to “α point”. In applying the vibrato, first, the fluctuation of the amplitude of the vibrato along the time axis is removed from the singing voice represented by the singing voice data. Then, the fluctuation of the vibrato amplitude is added to the singing voice from which the fluctuation of the amplitude is removed so that a set of vibrato amplitude and vibrato speed corresponding to the “α point” is formed.

  Then, the control part 50 displays the identification icon which is an aspect which can identify a correction object item and the non-correction object item which is a song evaluation item corresponding to a specific reference value (S210). The identification icon referred to here may be a character that can recognize the correction target item or various marks. Moreover, the identification icon said here may be the character of the aspect which can recognize an uncorrected object item, and various marks.

  Thereafter, the control unit 50 outputs the singing voice data corrected in S200 to the voice control unit 40. The voice control unit 40 outputs a voice signal represented by the corrected singing voice data to the speaker 60 via the output unit 42. Then, the speaker 60 outputs a voice represented by the corrected singing voice data.

Thereafter, the control unit 50 shifts the karaoke performance process to S230.
In S230, the control unit 50 determines whether or not the performance of the designated music has been completed. As a result of the determination in S230, if the performance of the designated music has not ended (S230: NO), the control unit 50 returns the karaoke performance processing to S140. In S140, the voice input via the microphone 62 and the microphone input unit 44 is acquired as singing voice data (S140).

On the other hand, if the result of determination in S230 is that the performance of the designated music has been completed (S230: YES), the controller 50 ends the karaoke performance processing. Then, the control unit 50 stands by until an activation command is input.
[Effect of the embodiment]
As described above, in the karaoke performance processing of the present embodiment, only the singing evaluation items with low evaluation in the singing voice data can be corrected and output as correction target items. Therefore, according to the karaoke performance process of this embodiment, the evaluation with respect to each singing evaluation item in the singing sound output from the karaoke apparatus 30 can be equalized, and the evaluation of the entire singing sound can be improved.

  In other words, according to the karaoke apparatus 30, the balance in the sound output from the karaoke apparatus 30 can be improved. As a result, according to the karaoke apparatus 30, the satisfaction level of the singer who is singing music can be improved.

  Furthermore, since the listener of the singing voice from the karaoke apparatus 30 can hear a well-balanced voice, the degree of satisfaction is improved. Therefore, according to the karaoke apparatus 30, the satisfaction degree of both a singer and a listener can be improved.

  By the way, in the karaoke performance processing, among the evaluation matching degrees for all singing evaluation items, singing evaluation items corresponding to all evaluation matching degrees lower than the specific reference value are set as correction target items, and all correction target items are Correction is made so that the evaluation coincidence of the correction target item approaches the specific reference value. Moreover, in the karaoke performance process, the highest evaluation coincidence among the evaluation coincidences for all singing evaluation items is set as the specific reference value.

For this reason, in the karaoke performance process, all other singing evaluation items in the singing voice data can be corrected based on the singing evaluation item having the highest evaluation.
As a result, according to the karaoke apparatus 30, the singing voice output from the karaoke apparatus 30 can be made into a more balanced voice, and the degree of satisfaction of both the singer and the listener can be further improved. .

  In the karaoke performance process of the present embodiment, an identification icon is displayed that is a mode in which a correction target item and a non-correction target item that is a singing evaluation item corresponding to the specific reference value can be identified.

Therefore, the user of the karaoke apparatus 30 can recognize the corrected singing evaluation item and the singing evaluation item that has not been corrected.
[Other Embodiments]
As mentioned above, although embodiment of this invention was described, this invention is not limited to the said embodiment, In the range which does not deviate from the summary of this invention, it is possible to implement in various aspects.

  For example, a plurality of predetermined periods in the above embodiment are set so as to be continuous along the time axis in the music, but the predetermined period in the present invention is not limited to this. That is, only one predetermined period in the present invention may be set in the music.

  In the present invention, when a plurality of predetermined periods are set, the plurality of predetermined periods are not limited to being set to be continuous along the time axis in the music. For example, the plurality of predetermined periods may be set for each predetermined timing so as to be discontinuous along the time axis of the music.

  Moreover, in the karaoke performance process of the said embodiment, although the audio | voice input during the performance of a designated music was evaluated sequentially, the evaluation timing which evaluates song audio | voice data is not restricted to this. For example, the singing voice data input during the performance of the designated music piece may be stored in the storage unit, and after the performance of the designated music piece is completed, the singing voice data stored in the storage unit may be collectively evaluated.

  In addition, the aspect which abbreviate | omitted a part of structure of the said embodiment is also embodiment of this invention. Further, an aspect configured by appropriately combining the above embodiment and the modification is also an embodiment of the present invention. Moreover, all the aspects which can be considered in the limit which does not deviate from the essence of the invention specified by the wording described in the claims are the embodiments of the present invention.

In addition to the above-described karaoke apparatus, the present invention evaluates the singing voice and corrects the singing voice reflecting the evaluation result, the program executed by the computer, the singing voice is evaluated, and the evaluation result is reflected. It can be realized in various forms such as a method of correcting to a singing voice.
[Correspondence between Embodiment and Claims]
Finally, the relationship between the description of the above embodiment and the description of the scope of claims will be described.

  The function obtained by executing S140 of the karaoke performance process in the above embodiment is an example of the voice acquisition means described in the claims, and the function obtained by executing S120 of the karaoke performance process is It is an example of the reference | standard acquisition means described in the claim. Further, the function obtained by executing S170 of the karaoke performance process is an example of the feature calculating means described in the claims, and the function obtained by executing S180 of the karaoke performance process is claimed. It is an example of the coincidence degree calculation means described in the range.

  The function obtained by executing S190 and S200 of the karaoke performance processing is an example of the correcting means described in the claims, and the function obtained by executing S220 is in the claims. It is an example of the described output means. Moreover, the function obtained by performing S210 of a karaoke performance process is an example of the display means described in the claim.

DESCRIPTION OF SYMBOLS 1 ... Karaoke system 10 ... Information processing server 12, 32 ... Communication part 14 ... Memory | storage part 16,50 ... Control part 18,52 ... ROM 20,54 ... RAM 22,56 ... CPU 30 ... Karaoke apparatus 34 ... Input reception part 36 ... Music reproduction unit 38 ... Storage unit 40 ... Audio control unit 42 ... Output unit 44 ... Microphone input unit 46 ... Video control unit 60 ... Speaker 62 ... Microphone 64 ... Display unit

Claims (5)

It is input via a microphone during the performance of a designated song that is a designated song among at least one song in which lyrics are assigned to at least a part of a plurality of notes consisting of a combination of pitch and note value. Voice acquisition means for acquiring singing voice data representing the voice,
A reference acquisition means for acquiring the evaluation reference data of the designated music from the evaluation reference data representing the evaluation reference of each of the plurality of evaluation items defined as items for evaluating the song of the music for each of the music,
Based on the singing voice data acquired by the voice acquisition means, feature calculating means for calculating a singing feature value representing the evaluation of the singing for each of the evaluation items in the singing voice data;
A degree of coincidence calculation that calculates, for each evaluation item, an evaluation coincidence that is a degree of coincidence between the singing feature amount calculated by the feature calculation unit and the evaluation criterion represented by the evaluation reference data acquired by the reference acquisition unit. Means,
For the at least one evaluation item whose evaluation coincidence calculated by the coincidence degree calculating means is lower than a specified specific reference value, acquired by the voice acquisition means so that the evaluation coincidence approaches the specific reference value Correction means for correcting the singing voice data;
An karaoke apparatus comprising: output means for outputting singing voice data corrected by the correcting means. The correction means includes
The karaoke apparatus according to claim 1, wherein the evaluation coincidence is corrected so that the evaluation coincidence approaches the specific reference value for all evaluation items whose evaluation coincidence is lower than the specific reference value. The correction means includes
The evaluation matching score of the highest evaluation item is set as the specific reference value,
The karaoke apparatus according to claim 1 or 2, wherein the evaluation matching degree is corrected so that the evaluation matching degree approaches a specific reference value for an evaluation item whose evaluation matching degree is lower than the specific reference value. Aspect capable of discriminating between at least one evaluation item whose evaluation coincidence calculated by the coincidence degree calculating means is lower than the specific reference value and at least one evaluation item whose evaluation coincidence is equal to or higher than the specific reference value The karaoke apparatus according to any one of claims 1 to 3, further comprising: a display unit configured to display the above. It is input via a microphone during the performance of a designated song that is a designated song among at least one song in which lyrics are assigned to at least a part of a plurality of notes consisting of a combination of pitch and note value. A voice acquisition step for acquiring singing voice data representing the voice,
A reference acquisition step for acquiring the evaluation reference data of the designated music from among the evaluation reference data representing the evaluation reference for each of a plurality of evaluation items defined as items for evaluating the song of the music for each music;
Based on the singing voice data acquired in the voice acquisition step, a feature calculating step for calculating a singing feature amount representing an evaluation of the singing for each of the evaluation items in the singing voice data;
A degree of coincidence calculation that calculates, for each evaluation item, an evaluation coincidence that is a degree of coincidence between the singing feature amount calculated in the feature calculation step and the evaluation criterion represented by the evaluation reference data acquired in the reference acquisition step. Steps,
Obtained in the voice acquisition step so that the evaluation coincidence approaches the specific reference value for at least one evaluation item whose evaluation coincidence calculated in the coincidence degree calculating step is lower than a specified specific reference value A correction step for correcting the singing voice data;
A program causing a computer to execute an output step of outputting singing voice data corrected in the correcting step.