JP6406273B2 - Karaoke device and program - Google Patents

Description

  The present invention relates to a karaoke apparatus that generates and outputs a virtual vocal, and a program that is executed by a computer included in the karaoke apparatus.

  As described in Patent Document 1, a karaoke apparatus is known that displays lyrics of the music in conjunction with the performance of the music. In this karaoke device, when karaoke music whose original singing is performed by a group singer composed of a plurality of singers is sung by more than a certain number of users of the group singer, the singing voice of the user and the singing of the singer Compare the voice with at least one of the sound quality and singing characteristics of the singing voice, assign different singing parts to each user in descending order of the similarity to the singer's singing part, and have multiple singing parts. A single tune is played and a plurality of users are allowed to sing group singers.

Japanese Patent Laying-Open No. 2015-45671

  However, when the number of users singing a song composed of a plurality of parts sung by a group singer is less than the number of parts of the group singer's song, using the technique described in Patent Document 1, the group singer There is a problem that the number of sounds is less than the performance sound of the original song being sung, and the reproducibility to the performance sound of the original song is low.

  Therefore, the present invention discriminates the part the user is singing when the karaoke performance sound of the music having a plurality of singing parts is reproduced, and the singing voice of the user who sings one of the singing parts An object of the present invention is to provide a karaoke apparatus that can perform a performance close to the original music by outputting performance sounds.

One aspect of the present invention made to achieve the above object relates to a karaoke apparatus comprising a reproducing means, an acquiring means, a generating means, a calculating means, a specifying means, and an output means.
The reproduction means reproduces an accompaniment sound of a designated music that is a designated music that is a music having a plurality of singing parts having at least a part of note attributes different from each other. The obtaining means obtains one or a plurality of sounds input through the microphone as song data during reproduction of the designated music by the reproducing means.

  Furthermore, the generating means is a general vocal in which the virtual vocal data whose number is equal to or greater than the difference between the number of singing parts in the designated music and the number of voices of the singing data and the singing data are mixed in correspondence with each singing part of the designated music. Is generated for each combination of singing parts of the designated music. Virtual vocal data is each of the singing voice which reproduced each singing voice of the plurality of singing parts in the designated music piece by the original singer's way of singing.

  For each of the integrated vocals generated by the generating means, the calculating means collates the singing voice of the designated song in which each of the plurality of singing parts is sung by the original singer with the comparative vocal, and determines the similarity with the comparative vocal. calculate. The specifying means specifies the total vocal having the highest similarity among the similarities calculated by the calculating means. The output means outputs the virtual vocal data included in the general vocal specified by the specifying means together with the reproduction of the accompaniment sound of the designated music.

  According to such a karaoke apparatus, it is possible to specify the general vocal most similar to the comparative vocal. This general vocal is the singing voice of the entire designated music obtained by supplementing the singing voice of the singing part other than the singing part in charge of the designated music with the virtual vocal data.

  And according to the karaoke apparatus, the virtual vocal data contained in the specified general vocal can be output. For this reason, according to a karaoke apparatus, the performance sound close | similar to the whole singing voice in an original music can be output by adding a user's singing voice to virtual vocal data, and outputting it.

  In other words, in a karaoke apparatus, when playing a song having a plurality of singing parts, a performance sound that is as close to the original song as possible is output in accordance with the song of the user who sings any singing part. be able to.

  The acquisition means in the karaoke apparatus may acquire each of a plurality of sounds input via each of the two or more microphones as song data. In this case, the generation means sets the plurality of song data acquired by the acquisition means to the song parts equal to or less than the number of song data, and for all combinations of the song parts of the plurality of song data, in the song data and the designated music piece You may produce | generate the integrated vocal which mixed the number of virtual vocal data more than the difference of the number of singing parts and the number of the singing parts set.

According to such a karaoke apparatus, each voice input via each of two or more microphones can be acquired as singing data, and one general vocal can be generated.
That is, according to the karaoke apparatus, even when a plurality of users sing, it is possible to specify the general vocal having the highest similarity and output appropriate virtual vocal data.

The production | generation means of a karaoke apparatus may produce | generate a general vocal about the combination whose song parts of several song data are respectively different song parts.
According to such a karaoke apparatus, even if each of a plurality of users sing a separate singing part, it is possible to specify a general vocal having the highest similarity.

  Moreover, the production | generation means of a karaoke apparatus may produce a general vocal about the combination including the case where the song part of the at least 2 song data of the some song data is the same song part.

According to such a karaoke apparatus, even when a plurality of users sing the same singing part, it is possible to specify a general vocal having the highest similarity.
Further, the karaoke device generating means corrects the power of the singing data so that the power of the singing data is within a range defined based on the power of at least one singing part in the virtual vocal data, and the general vocal May be generated.

  According to such a karaoke apparatus, it is possible to reduce the power of either the singing data or the virtual vocal data from becoming extremely large compared to the power of the other, and the other is in one of the singing data and the virtual vocal data. Burying can be reduced.

Thereby, according to a karaoke apparatus, the calculation precision of a similarity degree can be improved.
By the way, the output unit of the karaoke apparatus may include an adjustment unit, and may output either virtual vocal data or singing data adjusted by the adjustment unit. It is preferable that the adjustment unit performs adjustment so that at least one of the sound level in the virtual vocal data and the sound level of the song data is within a relatively specified range.

According to the karaoke apparatus, the volume balance of the entire output vocal can be adjusted.
As a result, according to the karaoke apparatus, it is possible to output a vocal sound closer to the entire original vocal.

By the way, one aspect of the present invention may be a program executed by a computer.
In this program, the playback procedure for playing back the accompaniment sound of the specified song, the acquisition procedure for acquiring singing data, the generation procedure for generating comprehensive vocals, the calculation procedure for calculating similarity, and the overall vocal with the highest similarity The computer is caused to execute a specific procedure for identifying the voice and an output procedure for outputting the virtual vocal data included in the general vocal together with the reproduction of the accompaniment sound of the designated music.

  If the present invention is implemented as a program, it can be used by loading the computer from a recording medium as needed and starting it, or by acquiring and starting the computer via a communication line as necessary.

  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 figure which shows schematic structure of a karaoke system. It is a flowchart which shows the process sequence of a virtual vocal output process. It is explanatory drawing explaining the 1st method of adjustment of power. It is explanatory drawing explaining the 2nd method of adjustment of power. It is a figure which shows the example of a combination of virtual vocal data and song data in a designated music, (A) is an example of a combination when there is one user, and (B) is a case where there are two users. It is a combination example. It is a flowchart which shows the process sequence of an optimal specific process. It is explanatory drawing explaining the calculation method of similarity.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.
<Karaoke system>
The karaoke system 1 shown in FIG. 1 includes an information processing server 10 and at least one karaoke device 30. The karaoke system 1 reproduces designated music that is music designated by the user of the karaoke apparatus 30.

  A song is a song of music in which lyrics are assigned to at least some of a plurality of notes arranged along the time axis, and is a song having a plurality of singing parts. A singing part is a voice part which each singer who comprises a music group sings. Each of the plurality of singing parts is different from each other in at least a part of the note attributes.

  The different note attributes in the singing part are the melody representing each singing part and the contents of the lyrics assigned to the notes constituting the melody. However, the note attributes that are different in the song part are not limited to this, it may be only the melody representing each song part, only the pitch of the note to which the lyrics are assigned, It may be only the content or other. That is, the note attributes are the pitch and value of a note, the lyrics assigned to the note, and the like.

The music group is a group composed of a plurality of original singers as performers who sang the music. This music group is, for example, a group that sings the song as a song. An original singer is a unique singer that constitutes a music group. The unique singer is a singer who sings in charge of each of a plurality of singing parts in the music.
<Information processing server>
The information processing server 10 includes a communication unit 12, a storage unit 14, and a control unit 16.

The communication unit 12 is connected to the karaoke apparatus 30 via a communication network, and the information processing server 10 communicates with the outside.
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 one MIDI musical piece MD, at least one virtual output data SD, and at least one comparative vocal CD, which will be described in detail later.

  Note that the symbol “n” shown in FIG. 1 is an identifier for identifying the MIDI music piece MD. This code “n” is a natural number of 1 or more. The code “l” is an identifier for identifying the virtual output data SD. This code “l” is a natural number of 1 or more. The code “m” is an identifier for identifying the comparative vocal CD. This code “m” 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 musical piece MD is data prepared in advance for each musical piece, and includes score data, lyrics data, and musical piece information.

  The musical score data is data representing the musical score of the accompaniment melody of one musical piece in accordance with the well-known MIDI (Musical Instrument Digital Interface) standard. In the musical score data, at least a pitch (so-called note number) and a note length are defined for each note that is reproduced and output from a MIDI sound source. The note length in the musical score data is defined by the note-on timing of the note and the note-off timing of the note. When the musical score data is reproduced, an accompaniment sound is output.

  The lyric data is data related to the lyrics of the music, and includes lyric text data representing the text of the lyrics of the music, and lyric output data in which the output timing of the text of the lyrics is associated with the reproduction of the music based on the score data. Yes.

The music information is information relating to the music, and includes a music ID and music group information.
The song ID is identification information for identifying a song. The music group information is information related to the music group. The music group information includes information representing a group ID for identifying the music group, the name of the music group, the name of the original singer, and the singing part that each original singer is in charge of.
<Comparison vocal and virtual output data>
The comparative vocal CD is a singing voice of one whole piece of music in which each of the singing parts is sung by the original singer constituting the music group. The comparative vocal CD is generated in advance for each music piece.

  As an example of a method for generating a comparative vocal CD, a method of identifying and separating a vocal sound by a known method from a master waveform in which an accompaniment sound of a musical instrument and a vocal sound are mixed in one piece of music can be considered.

  The virtual output data SD is data necessary for generating virtual vocal data, and is prepared in advance for each music group and each original singer. The virtual vocal data is each of the singing voices that express the singing voices of the plurality of singing parts in the designated music piece in the way of singing the original singer or the way of singing the original singer. The way of singing here includes voice quality in addition to singing techniques such as vibrato, shackles, and fist.

  The virtual output data SD in the present embodiment may be a singing voice in which the singing part of the music piece is sung by the original singer, or a singing voice in which the singing part of the music piece is sung by a singer that is similar to the original singer. Or data used for speech synthesis. The data used for speech synthesis may be a speech element used for waveform connection or a speech parameter used for formant synthesis.

When the virtual output data SD is data used for speech synthesis, the virtual output data SD includes feature data. Characteristic data refers to the characteristics of the singing method for each original singer for each combination of the pitch and note value of the note and the syllable of the lyrics assigned to the note so that the original singer's singing method is reproduced. It is data representing.
<Karaoke equipment>
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.

  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 reproducing unit 36 reproduces the accompaniment sound of the music 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.

  The microphone input unit 44 acquires sound input through at least one microphone 62. In the present embodiment, two microphones 62 are described as being connected to the microphone input unit 44, but the number of microphones 62 is not limited to two, and may be one, Three or more may be sufficient. The connection referred to here may be wired or wireless.

  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 sound 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 storage unit 38 is a well-known storage device configured to be able to read and write stored contents.
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.

In the ROM 52 of the present embodiment, a processing program for the control unit 50 to execute a virtual vocal output process of reproducing the accompaniment sound of the designated music, displaying the lyrics, and generating and outputting appropriate virtual vocal data. It is remembered.
<Virtual vocal output processing>
When the virtual vocal output process shown in FIG. 2 is activated, the control unit 50 first acquires the song ID of the song (ie, the designated song) designated via the input receiving unit 34 (S110). And the control part 50 acquires the MIDI music MD containing the music ID acquired by S110 from the memory | storage part 14 of the information processing server 10 (S120).

  And the control part 50 performs reproduction | regeneration of the accompaniment sound of a designated music based on the MIDI music MD acquired by S120 (S130). In S130, the control unit 50 sequentially outputs the MIDI music MD to the music playback unit 36 along the time axis. The music reproduction unit 36 that has acquired the MIDI music MD reproduces the accompaniment sound of the designated music, and outputs the sound source signal of the designated music to the speaker 60 via the output unit 42. Thereby, the performance sound of the designated music is emitted from the speaker 60.

  In S <b> 130, the control unit 50 further outputs lyrics output data and lyrics text data to the video control unit 46. Then, the video control unit 46 sequentially displays lyrics on the display unit 64 as the accompaniment sound of the designated music is reproduced.

  Subsequently, the control unit 50 acquires the number of users (hereinafter referred to as singing users) who are singing the designated music (S140). In S140, the control unit 50 may acquire, for example, the number of microphones 62 that are turned on as the number of singing users, or the number input via the input receiving unit 34 is the number of singing users. You may get as

  Further, in the virtual vocal output process, the control unit 50 acquires each voice input via each of the microphones 62 as song data and stores it in the storage unit 38 (S150). The singing data is the voice input through the microphone 62, that is, the singing voice that sang at least one singing part in the designated music piece.

  Then, the control unit 50 determines whether or not the reproduction of the comparison target section that is a predetermined section in the designated music has been completed (S160). As a result of the determination in S160, if the reproduction of the comparison target section has not ended (S160: NO), the control unit 50 returns the virtual vocal output process to S150. When the reproduction of the comparison target section ends (S160: YES), the control unit 50 shifts the virtual vocal output process to S170.

  In S170, the control unit 50 acquires virtual vocal data. Specifically, in S170 of the present embodiment, a singing voice in which the music is sung by the original singer, and a singing voice in which the music is sung by a singer similar to the original singer is prepared as the virtual output data SD. If there is, the control unit 50 acquires virtual output data SD corresponding to the designated music piece as virtual vocal data. When data used for speech synthesis is prepared as virtual output data SD, the control unit 50 includes the MIDI music MD (score data, lyrics data) acquired in S120 and feature data included in the virtual output data SD. To generate and acquire virtual vocal data by speech synthesis. In this case, the synthesized vocal is generated from the virtual vocal data as a singing voice reflecting the characteristics of the original singer in accordance with the score of each singing part.

  In the virtual vocal output process, the control unit 50 adjusts the power of the song data (S180). In S180, the control unit 50 corrects the power of the singing data so that the power of the singing data falls within a range defined based on the power of at least one singing part in the virtual vocal data.

Power is an index based on the amplitude of a speech waveform, for example, an index that means volume or sound pressure. An indicator based on the amplitude of the speech waveform also represents the level of sound intensity or volume.
The range defined as the reference is a range defined as the power at which the singing data is not buried in the virtual vocal data. Specifically, the range defined as the reference may be an average value of the power of a plurality of virtual vocal data as shown in FIG. 3, or corresponds to the song data as shown in FIG. The power of the virtual vocal data of the singing part may be used.

Then, the control part 50 produces | generates one comprehensive vocal which mixed the virtual vocal data produced | generated by S170, and the song data adjusted by S180 (S190).
The general vocal is a voice waveform in which singing data is mixed with virtual vocal data. The number of virtual vocal data mixed in the general vocal is a number greater than or equal to the difference between the number of singing parts in the designated music and the number of voices in the singing data.

  In S190, when the number of singing users is one, the control unit 50 sets one singing part for the singing data, and mixes the singing data with the combination of virtual vocal data for the remaining singing parts. In other words, the control unit 50 mixes the singing data by the singing user with one of the combinations obtained by combining the number of virtual vocal data obtained by subtracting “1” from the number of singing parts in the designated music piece. Thereby, one total vocal data is generated.

  Moreover, when there are a plurality of singing users, the control unit 50 may generate a general vocal, assuming that the singing part corresponding to each of the plurality of singing data is a separate singing part, The integrated vocal may be generated assuming that the singing parts corresponding to at least two of the singing data are the same singing part.

  That is, when there are a plurality of singing users, the control unit 50 determines the number of virtual vocals obtained by subtracting “the number equal to or less than the number” from the number of singing parts in the designated music for the target of mixing the singing data. One of the data combinations.

  Further, the control unit 50 determines whether or not a total vocal has been generated for all combinations of virtual vocal data and singing data (S200). As a result of the determination in S200, if the total vocals are not generated for all combinations (S200: NO), the control unit 50 returns the virtual vocal output process to S190. In S190, a total vocal that realizes one combination from the ungenerated combinations is generated.

If the integrated vocals are generated for all combinations (S200: YES), the control unit 50 shifts the virtual vocal process to S210.
In addition, with all combinations, for example, when the number of singing users is one for a song whose number of singing part types is “3”, as shown in FIG. The singing voice corresponding to one of the singing parts is singing data, and the singing voice corresponding to the remaining singing parts is the singing voice based on the virtual output data SD. Moreover, with all combinations, for example, when the number of singing users is two for a song whose number of types of singing parts is “3”, as shown in FIG. There are a total of six combinations. The six combinations include singing voices corresponding to each of the two singing parts as singing data, and singing voices corresponding to the remaining singing parts as singing voices based on the virtual output data SD, and one singing part. The three singing voices are the corresponding singing voices, and the singing voices corresponding to the remaining singing parts are the singing voices based on the virtual output data SD.

In S210, the control unit 50 executes the optimum specifying process. The optimum specifying process is a process for specifying the most appropriate comprehensive vocal. Details of the optimum specifying process will be described later.
Subsequently, the control unit 50 adjusts the sound level of the virtual vocal data constituting the most appropriate general vocal (S220). The adjustment of the sound level of the virtual vocal data in S220 is performed so that the sound level in one virtual vocal data is within a range defined relative to the sound level of the other virtual vocal data. The relatively defined range is a range defined in advance as a range of difference in sound level of each singing voice of the original singer in the designated music piece.

The sound level is an index that also represents the level of sound intensity or volume.
And the control part 50 outputs the virtual vocal data by which the sound level was adjusted in S220 to the output part 42 (S230). The output unit 42 outputs a virtual vocal represented by virtual vocal data from the speaker 60.

Furthermore, in S <b> 230, the control unit 50 outputs the song data to the output unit 42. The output unit 42 outputs singing data, that is, singing voice, from the speaker 60.
Thereafter, the control unit 50 ends the virtual vocal output process.
<Optimum specific processing>
In the optimum specifying process activated in S210 of the virtual vocal output process, as shown in FIG. 6, the control unit 50 first obtains a comparison vocal CD for the designated music piece from the storage unit 14 of the information processing server 10 ( S310). Subsequently, the control unit 50 calculates a comparison spectrum that is a spectrogram of the comparative vocal CD acquired in S310 (S320). Further, the control unit 50 smoothes the comparison spectrum calculated in S320 along the frequency axis for each unit time (S330).

  In the optimum specifying process, subsequently, the control unit 50 acquires one of the integrated vocals generated in the previous S190 (S340). And the control part 50 calculates the vocal spectrum which is the spectrogram of the general vocal acquired by S340 (S350). Further, the control unit 50 smoothes the vocal spectrum calculated in S350 along the frequency axis for each unit time (S360).

  Further, in the optimum specifying process, the control unit 50 collates the smoothed vocal spectrum with the smoothed comparison spectrum, and calculates the similarity (S370). The similarity is an index representing the correlation between the smoothed vocal spectrum and the smoothed comparison spectrum. The calculation of the similarity in S370 may be executed by obtaining the correlation between the smoothed vocal spectrum and the smoothed comparison spectrum.

  Subsequently, the control unit 50 determines whether or not the similarity with the comparative vocal CD is obtained for all the integrated vocals (S380). As a result of the determination in S380, if the similarity is not obtained for all the integrated vocals (S380: NO), the control unit 50 returns the optimum specifying process to S340. In S340, the control unit 50 acquires one general vocal from the general vocals whose similarity has not been calculated, and proceeds to S350. As a result, in the optimum specifying process, as shown in FIG. 7, the vocal spectra of all the general vocals are collated with the comparison spectrum, and the similarity to all the general vocals is obtained.

On the other hand, if the similarity has been calculated for all the general vocals (S380: YES), the control unit 50 shifts the optimum specifying process to S390.
In S390, the total vocal having the highest similarity among all the calculated similarities is specified as the most appropriate total vocal.

Thereafter, the control unit 50 ends the optimum specifying process and returns the process to S220 of the auxiliary vocal output process.
[Effect of the embodiment]
(1) As described above, according to the virtual vocal output process, it is possible to specify the general vocal most similar to the comparative vocal CD. This general vocal is the singing voice of the entire designated music obtained by supplementing the singing voice of the singing part other than the singing part in charge of the designated music with the virtual vocal data.

  According to the virtual vocal output process, virtual vocal data included in the specified general vocal can be output. Furthermore, in the virtual vocal output process, since the user's singing voice is output together with the singing voice represented by the virtual vocal data, the karaoke apparatus 30 can output a performance sound close to the entire singing voice in the original song.

  In other words, in the karaoke device 30, when playing a song having a plurality of singing parts, a performance sound that is as close to the original song as possible is output in accordance with the song of the user who sings any singing part. can do.

(2) In the virtual vocal output process, the power of the song data is corrected so that the power of the song data is within a specified range, and a general vocal is generated.
For this reason, according to the virtual vocal output processing, it is possible to reduce that the power of either one of the song data and the virtual vocal data is extremely large compared to the other power, and either the song data or the virtual vocal data can be reduced. It can reduce that the other is buried. Therefore, the calculation accuracy of the similarity can be improved.

  (3) In the optimum specifying process, both the comparison spectrum and the vocal spectrum are smoothed along the frequency axis for each unit time to calculate the similarity. For this reason, the similarity obtained by the optimum specifying process can be reduced from the influence of fine changes in the comparison spectrum and the vocal spectrum.

As a result, according to the virtual vocal output process, a more appropriate integrated vocal can be specified as the most appropriate integrated vocal.
(4) By the way, in the virtual vocal output process, when there are a plurality of singing users, the control unit 50 determines the target of mixing the plurality of singing data from the number of singing parts in the designated music as “the number or less. Each of the combinations of virtual vocal data of the number obtained by subtracting “number of”.

  That is, according to the virtual vocal output process, even when a plurality of users sing, it is possible to specify the general vocal with the highest similarity and output appropriate virtual vocal data.

  Furthermore, according to the virtual vocal output process, even when each of a plurality of users sing a separate singing part, even when a plurality of users sing the same singing part, Can identify the general vocal with the highest similarity.

  (5) In the virtual vocal output process, the virtual vocal data is recorded so that the sound level in one virtual vocal data is within a range defined relative to the sound level of the other virtual vocal data. The sound level is corrected.

For this reason, according to the virtual vocal output process, the volume balance of the entire vocal output from the speaker 60 can be adjusted so as to approach the entire singing voice of the master disk. Furthermore, a singing voice close to the volume balance of the entire singing voice of the master can be output.
[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.

  (1) For example, in the virtual vocal output process of the above embodiment, the object whose sound level is adjusted in S220 is the virtual vocal data, but the object whose sound level is adjusted may be song data.

(2) In the above embodiment, the execution subject of the optimum specifying process is the karaoke device 30, but the execution subject of the optimum specifying process may be the information processing server 10.
(3) 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.

(4) In addition to the karaoke apparatus described above, the present invention generates and outputs a virtual vocal by voice synthesis, a program executed by a computer included in the karaoke apparatus to generate and output a virtual vocal by voice synthesis. It can be realized in various forms such as a generation method.
[Example of correspondence]
The function obtained by executing S130 in the virtual vocal output process corresponds to an example of a playback unit. The function obtained by executing S150 corresponds to an example of an acquisition unit. The function obtained by executing S170 to S190 corresponds to an example of a generation unit. The function obtained by executing S230 corresponds to an example of an output unit.

  Furthermore, the function obtained by executing the optimum specifying processes S310 to S380 corresponds to an example of a calculation unit. The function obtained by executing S390 of the optimum specifying process corresponds to an example of the specifying unit.

  Note that the function obtained by executing S220 in the virtual vocal output process corresponds to an example of an adjusting unit.

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

Claims (7)

Reproduction means for reproducing the accompaniment sound of a designated song that is a song having a plurality of singing parts in which at least a part of the note attribute is different,
Obtaining means for obtaining one or a plurality of voices input via a microphone as singing data during reproduction of the designated music by the reproducing means;
Each singing voice that reproduces each singing voice of the plurality of singing parts in the designated music by the original singer's way of singing is assumed to be virtual vocal data, and the difference between the number of singing parts in the designated music and the number of voices of the singing data or more Generating means for generating, for each combination of singing parts of the designated music, a total vocal in which the number of the virtual vocal data and the singing data are mixed in correspondence with each singing part of the designated music;
And each of said overall vocal generated by said generating means, said collated with each of the plurality of singing part is singing the ratio較用vocals by the original singer, the similarity between the overall vocal and the comparative vocals A calculating means for calculating;
Among the similarities calculated by the calculating means, a specifying means for specifying a general vocal having the highest similarity,
A karaoke apparatus comprising: output means for outputting the virtual vocal data included in the general vocal specified by the specifying means together with reproduction of the accompaniment sound of the designated music piece. The acquisition means includes
Each of a plurality of voices input via each of two or more microphones is acquired as the singing data,
The generating means includes
The plurality of singing data acquired by the acquisition means are set as singing parts equal to or less than the number of the singing data, and for all combinations of the singing parts of the plurality of singing data, the singing data and the singing part in the designated music The karaoke apparatus according to claim 1, wherein the total vocal is generated by mixing the virtual vocal data having a number equal to or greater than a difference between the number of the vocal parts and the set number of the singing parts. The generating means includes
The karaoke apparatus according to claim 2, wherein singing parts of the plurality of singing data generate the integrated vocal for combinations that are different singing parts. The generating means includes
The karaoke apparatus of Claim 2 which produces the said integrated vocal about the combination including the case where the song part of the at least 2 song data among these song data is the same song part. The generating means includes
The total vocal is generated by correcting the power of the singing data so that the power of the singing data falls within a range defined based on the power of at least one singing part in the virtual vocal data. The karaoke apparatus according to any one of claims 1 to 4. The output means includes
Adjusting means for adjusting at least one of the sound level in the virtual vocal data or the sound level of the singing data within a relatively prescribed range;
The karaoke apparatus according to any one of claims 1 to 5, wherein either the virtual vocal data adjusted by the adjusting unit or the singing data is output. A program to be executed by a computer,
A reproduction procedure for reproducing an accompaniment sound of a designated song that is a designated song that is a song having a plurality of singing parts in which at least a part of the note attribute is different,
An acquisition procedure for acquiring one or a plurality of voices input via a microphone as song data during playback of the designated music piece according to the playback procedure;
Each singing voice that reproduces each singing voice of the plurality of singing parts in the designated music by the original singer's way of singing is assumed to be virtual vocal data, and the difference between the number of singing parts in the designated music and the number of voices of the singing data or more A generation procedure for generating, for each combination of singing parts of the designated music, a total vocal in which the number of the virtual vocal data and the singing data are mixed in correspondence with each singing part of the designated music;
And each of said overall vocal generated in the generation procedure, the collated with each of the plurality of singing part is singing the ratio較用vocals by the original singer, the similarity between the overall vocal and the comparative vocals A calculation procedure to calculate,
Among the similarities calculated in the calculating procedure, a specific procedure for specifying the general vocal with the highest similarity,
An output procedure for outputting the virtual vocal data included in the general vocal specified in the specific procedure together with the reproduction of the accompaniment sound of the designated music;
A program to be executed by the computer.