CN113870820A - Spectrum and voice synchronization method and terminal - Google Patents
Spectrum and voice synchronization method and terminal Download PDFInfo
- Publication number
- CN113870820A CN113870820A CN202111259601.0A CN202111259601A CN113870820A CN 113870820 A CN113870820 A CN 113870820A CN 202111259601 A CN202111259601 A CN 202111259601A CN 113870820 A CN113870820 A CN 113870820A
- Authority
- CN
- China
- Prior art keywords
- stop time
- time
- note
- music score
- audio
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10H—ELECTROPHONIC MUSICAL INSTRUMENTS; INSTRUMENTS IN WHICH THE TONES ARE GENERATED BY ELECTROMECHANICAL MEANS OR ELECTRONIC GENERATORS, OR IN WHICH THE TONES ARE SYNTHESISED FROM A DATA STORE
- G10H1/00—Details of electrophonic musical instruments
- G10H1/0008—Associated control or indicating means
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Reverberation, Karaoke And Other Acoustics (AREA)
Abstract
The invention discloses a spectrum and voice synchronization method and a terminal, wherein the first starting time of each word in singing lyrics of an audio to be played is determined according to the audio to be played; acquiring a music score file corresponding to the audio to be played, and determining a second start-stop time of each word in the singing lyrics corresponding to the music score file according to the music score file and the first start-stop time; determining the start-stop time of each note in the music score file according to the second start-stop time; aligning each word in the singing lyrics of the audio to be played and each word in the singing lyrics corresponding to the music score file, and then determining the start-stop time of the corresponding note in the music score file based on the start-stop time of each word in the aligned singing lyrics, so that the alignment of each tone of the audio to be played and each tone of the music score file corresponding to the tone can be realized, the synchronism of the tone played by the audio in the playing process and the tone to which the music score goes is improved, and the method is suitable for playing various songs.
Description
Technical Field
The invention relates to the field of audio processing, in particular to a spectrum and sound synchronization method and a terminal.
Background
In the process of playing songs, in order to enable a user to intuitively see which sound the played audio in the played songs is currently walking to, a music score and the audio are played synchronously, that is, the music score is synchronously played along with the playing of the audio. In most cases, the time of each beat in the audio is constant, so as long as the given speed in the music score is consistent with the playing speed of the song in the audio, the music score moves along the music score according to the given speed, and the synchronization of the music score and the audio can be maintained when the music score is played simultaneously, namely, the music score is played to which sound the audio is currently played, and the music score also moves to the position in the music score where the sound is located.
However, there are special cases where the time per beat in the audio is not constant, or the time per beat of a part of the sounds in the audio is not consistent with the time per beat of other sounds, such as a song with a tempo of a quarter note in one beat, a minute with 60 beats, i.e., 1 second for one beat, but the song has some or all of the places where the singer is free to play, the time per beat for the singer to play at these free places floats between 0.5 and 2 seconds, this results in a song that does not have a time per beat of 1 second for some or all of the song, and, at this time, if the music score is advanced at a speed given by the music score file, when the music is played synchronously with the audio, the problem that the start-stop time of partial tones or all notes of the music score is inconsistent with the start-stop time of the corresponding notes in the audio occurs, i.e. the spectrum sounds are not synchronized, i.e. the sound currently played by the audio is not the same sound as the sound currently gone to by the music score.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the method and the terminal for synchronizing the music score and the sound can improve the synchronism of the sound played by the audio and the sound of the music score going to the audio in the playing process.
In order to solve the technical problems, the invention adopts a technical scheme that:
a method of spectral tone synchronization comprising the steps of:
s1, determining the first start-stop time of each word in the singing lyrics of the audio to be played according to the audio to be played;
s2, acquiring a music score file corresponding to the audio to be played, and determining a second start-stop time of each word in the singing lyrics corresponding to the music score file according to the music score file and the first start-stop time;
and S3, determining the start-stop time of the corresponding note in the music score file according to the second start-stop time.
In order to solve the technical problem, the invention adopts another technical scheme as follows:
a spectrum sound synchronization terminal comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the computer program to realize the steps of the spectrum sound synchronization method.
The invention has the beneficial effects that: determining a first start-stop time of each character in the audio to be played according to the audio to be played, then determining a second start-stop time of each character in the singing lyrics corresponding to the music file according to the music file corresponding to the audio to be played and the first start-stop time, and then determining start-stop times of corresponding notes in the music file according to the second start-stop time; aligning each word in the singing lyrics of the audio to be played and each word in the singing lyrics corresponding to the music score file, and then determining the start-stop time of the corresponding note in the music score file based on the start-stop time of each word in the aligned singing lyrics, so that the alignment of each tone of the audio to be played and each tone of the music score file corresponding to the tone can be realized, the synchronism of the tone played by the audio in the playing process and the tone to which the music score goes is improved, and the method is suitable for playing various songs, such as variable-speed songs.
Drawings
FIG. 1 is a flow chart illustrating steps of a spectrum tone synchronization method according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a spectrum tone synchronization terminal according to an embodiment of the present invention;
FIG. 3 is a schematic representation of a music score of the song "Water county grandma bridge" cited in an embodiment of the present invention;
FIG. 4 is a diagram illustrating the correspondence between the waveform and the lyrics of the music score shown in FIG. 3 according to an embodiment of the present invention;
FIG. 5 is a diagram of a penultimate transcript of the song "leaves fluttering" cited in an embodiment of the present invention;
FIG. 6 is a diagram illustrating the correspondence between the waveform and the lyrics of the music score shown in FIG. 4 according to an embodiment of the present invention;
FIG. 7 is a diagram illustrating the correspondence between waveforms and notes of the music score shown in FIG. 4 according to an embodiment of the present invention;
FIG. 8 is a diagram illustrating the time duration adjustment of the notes shown in FIG. 7 according to an embodiment of the present invention;
FIG. 9 is a diagram illustrating the introduction of a song "leaves fluttering" according to an embodiment of the present invention;
FIG. 10 is a schematic diagram of the position of the prelude shown in FIG. 9 before adjustment according to an embodiment of the present invention;
FIG. 11 is a schematic diagram of the position of the adjusted introduction shown in FIG. 9 in accordance with an embodiment of the present invention;
FIG. 12 is a graphical representation of a music score according to an embodiment of the present invention;
FIG. 13 is a schematic representation of another music score referenced in accordance with an embodiment of the present invention;
FIG. 14 is a graph of a score including a polyphonic score according to an embodiment of the present invention;
FIG. 15 is a diagram of a score including a polyphonic score with vocal parts having independent lyrics in addition to a first vocal part according to an embodiment of the present invention.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
Referring to fig. 1, a spectrum tone synchronization method includes the steps of:
s1, determining the first start-stop time of each word in the singing lyrics of the audio to be played according to the audio to be played;
s2, acquiring a music score file corresponding to the audio to be played, and determining a second start-stop time of each word in the singing lyrics corresponding to the music score file according to the music score file and the first start-stop time;
and S3, determining the start-stop time of the corresponding note in the music score file according to the second start-stop time.
As can be seen from the above description, the beneficial effects of the present invention are: determining a first start-stop time of each character in the audio to be played according to the audio to be played, then determining a second start-stop time of each character in the singing lyrics corresponding to the music file according to the music file corresponding to the audio to be played and the first start-stop time, and then determining start-stop times of corresponding notes in the music file according to the second start-stop time; aligning each word in the singing lyrics of the audio to be played and each word in the singing lyrics corresponding to the music score file, and then determining the start-stop time of the corresponding note in the music score file based on the start-stop time of each word in the aligned singing lyrics, so that the alignment of each tone of the audio to be played and each tone of the music score file corresponding to the tone can be realized, the synchronism of the tone played by the audio in the playing process and the tone to which the music score goes is improved, and the method is suitable for playing various songs, such as variable-speed songs.
Further, the S1 further includes:
determining a third start-stop time of each note in the pure tone part of the audio to be played according to the audio to be played;
the S3 further includes:
and determining the fourth starting and stopping time of each note in the pure tone part corresponding to the music score file according to the music score file and the third starting and stopping time.
As can be seen from the above description, since the audio to be played includes both the lyric part and the pure note part without lyrics and with notes, the third start-stop time of each note included in the audio to be played is determined according to the pure note part, and then the fourth start-stop time of each note in the pure note part is determined according to the music score file and the third start-stop time, so as to further ensure the synchronism of the audio playing sound and the music score going to.
Further, the determining a second start-stop time of each word in the singing lyrics corresponding to the music score file according to the music score file and the first start-stop time comprises:
expanding the singing lyrics corresponding to the music score file according to the time sequence according to the preset speed in the music score file;
and adjusting the singing lyrics corresponding to the music score file expanded according to the time sequence according to the first start-stop time of each word in the singing lyrics of the audio to be played to obtain the second start-stop time of each word in the singing lyrics corresponding to the music score file.
According to the description, the corresponding singing lyrics are unfolded according to the time sequence according to the preset speed in the music score file, and then the unfolded singing lyrics are adjusted through the first start-stop time, so that the alignment of the unfolded singing lyrics and the first start-stop time of each word is realized, and the synchronism of the audio playing sound and the music score arriving sound in the playing process is ensured.
Further, before determining the start-stop time of each note in the music score file in S3, the method further includes:
and correcting target start-stop time according to the audio to be played, wherein the target start-stop time comprises at least one of the second start-stop time, the fourth start-stop time and start-stop time of corresponding notes determined by the second start-stop time.
As can be seen from the above description, before the start-stop time of each note in the music score file is determined, at least one of the second start-stop time, the fourth start-stop time, and the start-stop time of the corresponding note determined by the second start-stop time is corrected according to the audio to be played, so that the synchronism between the audio played sound and the music score going to the sound in the playing process is further ensured. In the correction process, since the second start-stop time affects the start-stop time of the corresponding note determined by the second start-stop time, the correction of the second start-stop time may be performed first, and then the correction of the start-stop time of the corresponding note determined by the second start-stop time may be performed.
Further, the correcting the target start-stop time according to the audio to be played includes:
converting the audio to be played into a waveform in a time domain;
determining a starting point and a terminating point of each target object of the audio to be played according to the waveform, wherein when the target starting and stopping time is a second starting and stopping time, the target object is a word in the lyrics to sing, and when the target starting and stopping time is a fourth starting and stopping time, the target object is a note in the pure tone part; when the target start-stop time is the start-stop time of the corresponding note determined by the second start-stop time, the target object is the corresponding note determined by the second start-stop time;
and correcting the target start-stop time corresponding to each target object according to the start point and the end point of each target object.
As can be seen from the above description, by converting the audio to be played into a time domain waveform, determining the start point and the end point of each word or each corresponding note of each word in the lyric (i.e. the corresponding note determined by the second start-stop time) or each note in the pure tone part based on the waveform, and then correcting the second start-stop time corresponding to each word or the third start-stop time corresponding to each note and the start-stop time of the corresponding note determined by the second start-stop time based on the start point and the end point of each word or each note, the synchronism of the audio played sound and the music score walking to the music score during the playing process is further ensured by means of waveform correction.
Further, the determining a start point and an end point of each target object of the audio to be played according to the waveform includes:
traversing each time point in the waveform in a time order, for the traversed time point:
judging whether the amplitude of the waveform is increased to be more than a first preset proportion of the maximum amplitude of the waveform within a first preset time from the time point, if so, the time point is the starting point of a target object;
if not, judging whether the amplitude of the waveform is reduced to be below a second preset proportion of the maximum amplitude of the waveform within a second preset time from the time point, if so, the time point is the end point of a target object;
otherwise, continuously traversing the next time point in the waveform until each time point in the waveform is traversed;
and determining the starting point and the ending point of each target object of the audio to be played according to the starting points and the ending points of all the target objects determined after the traversal is completed.
As can be seen from the above description, by traversing each time point in the waveform, and for the traversed time point, by comparing the magnitude relationship between the waveform amplitude within the preset time taking the time point as the starting point and the maximum amplitude of the waveform, the starting point and the ending point of each target object in the singing lyrics of the audio to be played can be accurately identified.
Further, the correcting the target start-stop time according to the audio to be played includes:
playing the audio to be played, performing voice recognition or tone recognition on the audio to be played, determining a starting point and a terminating point of each target object in the singing lyrics or the playing music of the audio to be played, wherein when the target starting and stopping time is a second starting and stopping time, the target object is a word in the singing lyrics, and when the target starting and stopping time is a fourth starting and stopping time, the target object is a note in the pure tone character part in the playing music; when the target start-stop time is the start-stop time of the corresponding note determined by the second start-stop time, the target object is the corresponding note determined by the second start-stop time;
and correcting the target start-stop time corresponding to each target object according to the start point and the end point of each target object.
From the above description, it can be known that, by performing automatic speech recognition or pitch recognition on the audio to be played, determining the starting point and the ending point of each target object in singing lyrics or playing music, and correcting the target starting and ending time based on the determined starting point and ending point of each target object, the correction of the target starting and ending time is quickly and conveniently realized in a speech recognition or pitch recognition manner.
Further, the correcting the target start-stop time according to the audio to be played includes:
correspondingly displaying each target object of the audio to be played according to the target start-stop time and the playing sequence, wherein adjacent target objects are distinguished by different color blocks, the start-stop position of each color block on a time axis represents the start-stop time corresponding to each target object, the length of each color block on the time axis represents the time length corresponding to each target object, when the target start-stop time is the second start-stop time, the target objects are characters in the singing lyrics, and when the target start-stop time is the fourth start-stop time, the target objects are notes in the pure tone part; when the target start-stop time is the start-stop time of the corresponding note determined by the second start-stop time, the target object is the corresponding note determined by the second start-stop time;
playing the audio to be played, and synchronously displaying a progress bar on the color block in the playing process;
receiving an adjusting instruction sent by an operation object according to the deviation between the played audio and a target object indicated by the progress bar;
and correcting the target start-stop time according to the adjusting instruction.
According to the description, the time length corresponding to each target object in the audio to be played is displayed in different color block forms, the progress bars are synchronously displayed, and the operation object can dynamically adjust the color blocks corresponding to the target objects in real time based on the audio heard by the operation object and the progress bars so as to realize the correction of the start-stop time of the target, so that the operation object is visual and convenient.
Further, the adjusting instruction comprises a color block to be adjusted and an adjusting mode;
the correcting the target start-stop time according to the adjustment instruction comprises:
adjusting the starting and ending time boundary of the color block to be adjusted in the time axis direction according to the color block to be adjusted and the adjusting mode; or dragging the whole color block to be adjusted along the direction of a time axis;
and determining the target start-stop time according to the start-stop position of the adjusted color block on the time axis.
According to the above description, when the color block is adjusted, different adjustment modes can be set to perform corresponding adjustment, so that the target start-stop time is corrected, and the convenience and flexibility of correcting the target start-stop time are realized.
Further, the determining the start-stop time of the corresponding note in the music score file according to the second start-stop time includes:
and determining the start-stop time of each note in the music score file according to the corresponding relation between the lyrics and the notes, the proportional relation between the note durations and the second start-stop time.
As can be seen from the above description, when determining the start-stop time of a note, the accuracy of the determined start-stop time of the note can be ensured by considering not only the correspondence between the lyrics and the note, but also the proportional relationship between the values of the notes.
Further, the determining the start-stop time of each note in the music score file according to the corresponding relationship between the lyrics and the notes, the proportional relationship between the note durations and the second start-stop time comprises:
executing the following steps for each word in the audio to be played:
determining the number of notes corresponding to the words according to the corresponding relation between the lyrics and the notes;
if the number of the notes corresponding to the word is one, the start-stop time of the notes corresponding to the word is the second start-stop time corresponding to the word;
if the number of the notes corresponding to the word is more than two, determining the proportional relation of note duration values among the notes corresponding to the word;
and determining the start-stop time corresponding to each note corresponding to the word according to the proportional relation of the note duration and the second start-stop time corresponding to the word.
According to the description, the start-stop time corresponding to each note is determined according to the corresponding relation between each word of the singing lyrics in the audio to be played and the audio and the proportional relation of the note duration between the notes corresponding to each word, and the accuracy of the determined start-stop time corresponding to each note is guaranteed.
Further, the S3 further includes:
judging whether the music score file contains a plurality of voice part music scores or not;
if yes, after the start-stop time of each corresponding note of one first sound part music score is determined, the start-stop time of each note corresponding to the rest sound part music scores is determined according to the corresponding relation between the rest sound part music scores and the notes of the first sound part music scores.
As can be seen from the above description, for the polyphonic part melody, after the start and stop time of each note in one of the polyphonic part melody is determined, the start and stop time of each note in the other polyphonic part melody can be directly determined based on the determined part melody, which is convenient and fast.
Further, the determining the start-stop time of each note corresponding to the rest part music score according to the corresponding relationship between the rest part music score and the notes of the first part music score includes:
judging whether the notes of the rest part music score and the notes of the first part music score are in one-to-one correspondence in the same time period and have the same note duration, if so, determining the start-stop time of each note of the rest part music score according to the start-stop time of each note of the first part music score in the same time period;
and if not, determining the start-stop time of each note of the rest part music score according to the proportional relation between the start-stop time and the note duration of each note of the first part music score and the note duration of each note of the rest part music score in the same time period.
As can be seen from the above description, when the start-stop time of each note of the sound part score to be determined is determined according to the relationship between the notes of different sound part scores, the accuracy of the start-stop time corresponding to each determined note is ensured by considering the interrelation between the notes of different sound part scores and also considering the proportional relationship between the note durations of the notes of the sound part score to be determined.
Further, judging whether the music score file contains a plurality of vocal parts music scores and the vocal parts with independent lyrics exist except the first vocal part;
if so, after the start-stop time of each corresponding note of the qualified vocal part music score is determined, the start-stop time of each lyric of the qualified vocal part music score is determined according to the corresponding relation between each lyric of the qualified vocal part music score and the corresponding note of the qualified vocal part music score and the proportional relation between the start-stop time of each note of the qualified vocal part music score and the note time value.
As can be seen from the above description, when the music score file includes a plurality of vocal part music scores and a vocal part with independent lyrics exists except for the first vocal part, after the start-stop time of each note of the qualified vocal part music score is determined, the start-stop time of each lyric of the qualified vocal part music score can be determined according to the corresponding relationship between each lyric of the qualified vocal part music score and the note of the qualified vocal part music score and the proportional relationship between the start-stop time and the note time value of each note of the qualified vocal part music score, so that the start-stop time of each lyric of the qualified vocal part music score can be conveniently and quickly determined.
As shown in fig. 2, a spectrum tone synchronization terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the spectrum tone synchronization method when executing the computer program.
Example one
Referring to fig. 1, a spectrum tone synchronization method includes the steps of:
s1, determining the first start-stop time of each word in the singing lyrics of the audio to be played according to the audio to be played;
specifically, voice in the audio to be played is separated, and the first starting time of each word singing the lyrics in the audio to be played is determined according to the separated voice;
wherein, the voice in the song audio can be separated by adopting a D3NET algorithm or a Spleeter algorithm and the like; then, determining the first ending time of each word singing lyrics in the audio to be played by using a GOP algorithm from the separated voice;
s2, acquiring a music score file corresponding to the audio to be played, and determining a second start-stop time of each word in the singing lyrics corresponding to the music score file according to the music score file and the first start-stop time;
specifically, according to a preset speed in the music score file, expanding the singing lyrics corresponding to the music score file according to a time sequence;
if the music score file has repeated marks, the music score is expanded according to the repeated mark information;
adjusting the singing lyrics corresponding to the melody spectrum file expanded according to the time sequence according to the first start-stop time of each word in the singing lyrics of the audio to be played to obtain the second start-stop time of each word in the singing lyrics corresponding to the melody spectrum file;
wherein, the adjustment is specifically as follows: aligning the expanded lyrics with the first start-stop time of each word according to the time sequence, thereby re-determining the start-stop time of the expanded lyrics in the audio frequency;
and S3, determining the start-stop time of the corresponding note in the music score file according to the second start-stop time.
Example two
The embodiment further defines the determination of the start-stop time of the note of the pure tone part of the audio to be played, specifically:
the S1 further includes:
determining a third start-stop time of each note in the pure tone part of the audio to be played according to the audio to be played;
the pure tone character part of the audio to be played comprises a part which has no singing lyrics and only plays notes in the audio to be played, such as a prelude, a transition between a master song and a refrain and the like;
the S3 further includes:
and determining the fourth starting and stopping time of each note in the pure tone part corresponding to the music score file according to the music score file and the third starting and stopping time.
EXAMPLE III
The present embodiment further defines that before determining the start-stop time of each note in the music score file in S3, the method further includes:
correcting a target start-stop time according to the audio to be played, wherein the target start-stop time comprises at least one of the second start-stop time, the fourth start-stop time and the start-stop time of the corresponding note determined by the second start-stop time;
that is, the second start-stop time or the fourth start-stop time or the start-stop time of the corresponding note determined by the second start-stop time may be corrected, and the second start-stop time, the fourth start-stop time, and the start-stop time of the corresponding note determined by the second start-stop time may be corrected at the same time;
in an alternative embodiment, when the second start-stop time is corrected, then S3 includes:
correcting the second start-stop time according to the audio to be played, and determining the start-stop time of corresponding notes in the music score file based on the corrected second start-stop time;
in an alternative embodiment, when the fourth start time is corrected, then S3 includes:
correcting the fourth starting and stopping time according to the audio to be played;
in an alternative embodiment, when the start-stop time of the corresponding note determined by the second start-stop time is corrected, then S3 includes:
correcting the second start-stop time according to the audio to be played, and determining the start-stop time of corresponding notes in the music score file based on the corrected second start-stop time; the start-stop time of the corresponding note determined by the corrected second start-stop time is then corrected.
EXAMPLE III
This embodiment specifically defines a manner how to correct the target start-stop time according to the audio to be played:
converting the audio to be played into a waveform in a time domain;
determining a starting point and a terminating point of each target object of the audio to be played according to the waveform, wherein when the target starting and stopping time is a second starting and stopping time, the target object is a word in the lyrics to sing, and when the target starting and stopping time is a fourth starting and stopping time, the target object is a note in the pure tone part; when the target start-stop time is the start-stop time of the corresponding note determined by the second start-stop time, the target object is the corresponding note determined by the second start-stop time;
correcting the target start-stop time corresponding to each target object according to the start point and the end point of each target object;
wherein determining a start point and an end point of each target object in the audio to be played according to the waveform comprises:
traversing each time point in the waveform in a time order, for the traversed time point:
judging whether the amplitude of the waveform is increased to be more than a first preset proportion of the maximum amplitude of the waveform within a first preset time from the time point, if so, the time point is the starting point of a target object;
if not, judging whether the amplitude of the waveform is reduced to be below a second preset proportion of the maximum amplitude of the waveform within a second preset time from the time point, if so, the time point is the end point of a target object;
otherwise, continuously traversing the next time point in the waveform until each time point in the waveform is traversed;
determining the starting point and the ending point of each target object of the audio to be played according to the starting points and the ending points of all the target objects determined after traversal is completed;
the first preset time, the first preset proportion, the second preset time and the second preset proportion can be flexibly and adaptively changed according to different songs;
taking the song "shui xiang grandma bridge" shown in fig. 3 as an example, the uppermost black waveform in fig. 4 is a waveform in a time domain corresponding to an audio to be played, the center of the waveform is set to be 0, the amplitude of the waveform fluctuates up and down along with the change of sound, the larger the volume of the sound is, the larger the amplitude of the fluctuation up and down is, when a certain lyric starts to sing, the fluctuation amplitude is suddenly increased to more than half of the maximum amplitude of the waveform within 0.05 seconds, so as to determine the sing start time of the lyrics, when a certain lyric finishes sing, the fluctuation amplitude is reduced to less than 20% of the maximum amplitude of the waveform along with the reduction of the sing volume, so as to determine the sing end time of the lyrics, the color blocks of different colors below the black waveform are the start and end times of each lyric corresponding to the lyric when the music spectrum is spread (the left and right edges of each color block represent the start and end times of each lyric, and the length of the color block represents the length of one lyric to sing, the words in the color block represent lyrics), time scales are arranged below the color block (the minimum scale unit is 100 milliseconds), a vertical line from a black waveform to the time scales is a progress bar of the current playing progress, and playing progress control is arranged below the time scales, namely after the starting and stopping time of each word in the lyrics is determined according to a waveform diagram, the starting and stopping positions of the color block corresponding to each word on a time axis can be dynamically adjusted directly according to the displayed content;
when the audio is played, the playing progress bar can also move to the waveform time corresponding to the current audio playing time, so that the relation between the audio and the waveform can be observed more visually, and the corresponding relation between the lyrics and the lyrics in the audio and the waveform can be determined.
Example four
The embodiment specifically defines another way how to correct the target start-stop time according to the audio to be played:
playing the audio to be played, performing voice recognition or tone recognition on the audio to be played, determining a starting point and a terminating point of each target object in the singing lyrics or the playing music of the audio to be played, wherein when the target starting and stopping time is a second starting and stopping time, the target object is a word in the singing lyrics, and when the target starting and stopping time is a fourth starting and stopping time, the target object is a note in the pure tone character part; when the target start-stop time is the start-stop time of the corresponding note determined by the second start-stop time, the target object is the corresponding note determined by the second start-stop time;
correcting the target start-stop time corresponding to each target object according to the start point and the end point of each target object;
the embodiment provides a mode for automatically correcting the start-stop time of a target, namely, firstly, identifying whether the lyrics sung currently are consistent with the lyrics in a corresponding music score or whether the notes played currently are consistent with the notes in the corresponding music score through voice recognition or tone recognition, and if not, automatically adjusting;
in another alternative embodiment, after the automatic adjustment is completed, the correction can be performed again by adopting the three waveform correction of the embodiment.
EXAMPLE five
The embodiment specifically defines another way how to correct the target start-stop time according to the audio to be played:
correspondingly displaying each target object of the audio to be played according to the target start-stop time and the playing sequence, wherein adjacent target objects are distinguished by different color blocks, the start-stop position of each color block on a time axis represents the start-stop time corresponding to each target object, the length of each color block on the time axis represents the time length corresponding to each target object, when the target start-stop time is the second start-stop time, the target objects are characters in the singing lyrics, and when the target start-stop time is the fourth start-stop time, the target objects are notes in the pure tone part; when the target start-stop time is the start-stop time of the corresponding note determined by the second start-stop time, the target object is the corresponding note determined by the second start-stop time;
playing the audio to be played, and synchronously displaying a progress bar on the color block in the playing process;
receiving an adjusting instruction sent by an operation object according to the deviation between the played audio and a target object indicated by the progress bar;
correcting the target start-stop time according to the adjusting instruction;
the adjusting instruction comprises a color block to be adjusted and an adjusting mode;
the correcting the second start-stop time according to the adjustment instruction comprises:
adjusting the starting and ending time boundary of the color block to be adjusted in the time axis direction according to the color block to be adjusted and the adjusting mode; or dragging the whole color block to be adjusted along the direction of a time axis;
determining the target start-stop time according to the start-stop position of the adjusted color block on a time axis;
specifically, as shown in fig. 4, when the audio is played, the progress bar moves forward, and the user can determine whether the singing time of the currently played lyrics is consistent with the lyrics of the corresponding color block in the progress bar by listening to the audio, and if not, can adjust the start and stop of the color block (the left and right boundaries of each color block can extend leftwards and rightwards, the color block can also be dragged leftwards and rightwards integrally, and the whole shift of all the color blocks or the shift of the middle color block can be performed), so as to ensure that the lyrics at the corresponding moment in the audio are consistent with the start and stop time of the lyrics in the color block, and the lyrics continuously played back and forth in the audio are consistent with the lyrics continuously appeared back and forth in the color block, and through adjustment, the time of all the lyrics after being expanded in the music score can be consistent with the time of the corresponding lyrics in the audio, and the lyrics can be stored;
in an optional implementation manner, the process of manual adjustment of the present embodiment may be further performed on the basis of the fourth embodiment:
for example, taking the penultimate subsection of the song "leaves fluttering" shown in fig. 5 as an example, the start-stop time corresponding to the words "see" and "wind" of the lyrics is shown in fig. 6, and the time after the operation of the third embodiment of the start-stop time of each note is shown in fig. 7; at this time, if the audio is listened to and the time of "seeing" the sound 5 is not so much found, the left and right boundaries of the color block of the sound 5 may be dragged to be aligned with the audio, as shown in fig. 8;
when the start-stop time of the note corresponding to the prelude is adjusted, the above adjustment mode based on the lyrics of the color block can be adopted, and because the prelude has no lyrics, when the music score is synchronized, the start-stop position of the color block can be adjusted while listening to the audio frequency, watching the waveform, such as the prelude diagram of the song "leaves drifting" as shown in fig. 9, fig. 10 is the position of the prelude before adjustment, and fig. 11 is the position of the prelude after adjustment.
EXAMPLE six
This embodiment specifically defines how to determine the start-stop time of each note in the music score file based on the second start-stop time:
determining the start-stop time of each note in the music score file according to the corresponding relation between the lyrics and the notes, the proportional relation between the note durations and the corrected second start-stop time of each word;
specifically, the following steps are performed for each word in the audio to be played:
determining the number of notes corresponding to the words according to the corresponding relation between the lyrics and the notes;
if the number of the notes corresponding to the word is one, the start-stop time of the notes corresponding to the word is the second start-stop time corresponding to the word;
if the number of the notes corresponding to the word is more than two, determining the proportional relation of note duration values among the notes corresponding to the word;
determining the start-stop time corresponding to each note corresponding to the word according to the proportional relation of the note duration and the second start-stop time corresponding to the word;
for example, if the third lyric "young" in fig. 3 corresponds to only one note 5, the start-stop time of the note 5 is consistent with the start-stop time of the lyric "young";
for example, the third lyric "me" shown in fig. 12 corresponds to four notes, i.e., 5, 1, 3, and 5, and since the four notes are all octants, i.e., the singing time is the same, the four notes equally divide the lyric "me" time, i.e., the start-stop time of the four notes can be obtained;
for example, as shown in fig. 13, the fourth lyric "song" has four notes corresponding to the first four notes, i.e., the eighth note 5, the sixteenth note 6, the eighth note 7 and the eighth note 6, and because the four notes have different durations, the four notes have different time lengths in the lyric, the first note occupies 37.5% of the lyric, the second note occupies 12.5% of the lyric, and the third and fourth notes both occupy 25% of the lyric, so as to obtain the start-stop time of the four notes;
when the audio and the music score are played, the music score moves along the music score according to the lyrics and the time of the notes determined by the embodiment, so that the synchronization with the audio playing can be realized (namely which lyrics of which notes are played at the moment of the audio, and the music score also moves to the positions of the notes and the lyrics), namely the synchronization of the music and the music.
The three ways of correcting the target start-stop time described in the third to sixth embodiments may be applied in different combinations as required to further improve the synchronization effect.
EXAMPLE seven
The embodiment describes how to determine the start-stop time of each note in the multi-tone part score application scenario, specifically:
the S3 further includes the steps of:
judging whether the music score file contains a plurality of voice part music scores or not;
if so, after the start-stop time of each corresponding note of one of the vocal part music scores is determined, the start-stop time of each corresponding note of the rest of the vocal part music scores is determined according to the corresponding relation between the rest of the vocal part music scores and the notes of the one of the vocal part music scores;
wherein determining the start-stop time of each note corresponding to the rest of the vocal part music score according to the corresponding relationship between the rest of the vocal part music score and the notes of the first vocal part music score comprises:
judging whether the notes of the rest part music score and the notes of the first part music score are in one-to-one correspondence in the same time period and have the same note duration, if so, determining the start-stop time of each note of the rest part music score according to the start-stop time of each note of the first part music score in the same time period;
if not, determining the start-stop time of each note of the rest part music score according to the proportional relation between the start-stop time and the note duration of each note of the first part music score and the note duration of each note of the rest part music score in the same time period;
as shown in fig. 14, for the partial music score information of the song hunter chorus, it can be seen from the figure that this line is composed of two vocal parts, and assuming that the notes in the upper line in the figure are synchronized with the spectrum sound and the notes in the lower line are not synchronized with the spectrum sound, when the time of the audio frequency in the lower line is calculated, the time of the notes in the upper line is synchronized, so as to achieve the purpose of synchronous display of the notes when the two vocal parts are played;
the specific method comprises the following steps:
extracting a time value and a start-stop time corresponding to each sound of the corresponding measure in the previous row according to the front-back sequence; analyzing the time values of each note of the next row corresponding to the measure in the front-back sequence, determining which notes of the next row correspond to those of the previous row through the time values (the notes of different parts in the same time period may be one-to-one, many-to-one or one-to-many), and assigning the time corresponding to the notes of the previous row to the corresponding notes of the next row;
for example, in the figure, the first measure has three notes 4, 3 in the first sound part, the duration of the sounds is quarter note, eighth note, and corresponding measure has three notes 6, 1 in the second sound part, the duration of the corresponding sounds is quarter note, eighth note, and since the durations of the corresponding notes are the same, the start and stop times of the three sounds in the second sound part are the same as the start and stop times of the corresponding three sounds in the first sound part;
two sounds 0 and 0 are provided in the fourth bar of the first sound part, the duration of the sounds is quarter note and quarter note, six sounds 5, 5 and 5 are provided in the fourth bar of the second sound part, the duration of the sounds is eighth note, sixteenth note, the first three notes of the fourth bar of the second sound part are proportional in time value, the start and stop time of each sound is determined according to the start and stop time of the first sound of the fourth bar of the first sound part, and the last three sounds of the fourth bar of the second sound part are processed in the same way.
Example eight
The embodiment describes how to determine the starting and stopping time of the lyrics of the vocal part with the independent lyrics except the first vocal part in the application scenario of the multi-vocal part melody spectrum, and specifically:
judging whether the music score file contains a plurality of vocal parts music scores and the vocal parts with independent lyrics exist except the first vocal part;
if so, after the start-stop time of each corresponding note of the qualified vocal part music score is determined, the start-stop time of each lyric of the qualified vocal part music score is determined according to the corresponding relation between each lyric of the qualified vocal part music score and the corresponding note of the qualified vocal part music score and the proportional relation between the start-stop time of each note of the qualified vocal part music score and the note time value. As shown in fig. 14, after the start-stop time of each note of the second sound part is obtained according to the seventh embodiment, the start-stop times of several lyrics corresponding to the second sound part can be obtained;
the method comprises the following steps:
in fig. 14, only the third and fourth bars of the second vocal part have lyrics, and each lyric corresponds to a note, the start-stop time of the corresponding note is the start-stop time of the corresponding lyric. That is, the first lyric "la" corresponds to the second note 5 of the third measure of the second vocal part, and the start-stop time of the note is the start-stop time of the corresponding lyric; if the second lyric "la" corresponds to the first note 5 of the fourth bar of the second vocal part, the start-stop time of the note is the start-stop time of the corresponding lyric;
as shown in fig. 15, the song spectrum segment of song "quiet night thought" has lyrics for each measure of the second vocal part, and the number of notes corresponding to each lyric is different, so that the start time of each lyric is the start time of the corresponding first note, and the end time of each lyric is the end time of the corresponding last note. For example, the second lyric "head" of the second bar is arranged with two notes before and after 1 and 6, the start time of the lyric is the start time corresponding to the first note 1 and the end time of the lyric is the end time corresponding to the last note 6. If the first lyric of the third subsection, month, has four notes arranged in front of and behind 3, 5, 2 and 3, the start time of the lyric is the start time corresponding to the first note 3, and the end time of the lyric is the end time corresponding to the last note 3.
Example nine
Referring to fig. 2, a spectrum sound synchronization terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the spectrum sound synchronization method according to any one of the first to seventh embodiments.
In summary, according to the spectrum and sound synchronization method and the terminal provided by the present invention, a first start-stop time of each word in the lyrics of the audio to be played and a third start-stop time of each note in the pure tone character part are determined according to the audio to be played, a second start-stop time of each word in the lyrics corresponding to the music file and a fourth start-stop time of each note in the pure tone character part are determined according to the music file, the first start-stop time and the third start-stop time corresponding to the audio to be played, the second start-stop time and the fourth start-stop time are corrected according to the audio to be played, and finally the start-stop time of each note in the music file is determined according to the corrected second start-stop time and fourth start-stop time; aligning each note of each word and pure tone part of the lyrics in the audio to be played based on each note in each word and pure tone part of the lyrics to be played and each note of each word and pure tone part of the lyrics to be played corresponding to the lyrics file, further correcting the start-stop time of each aligned word and each note in the music file based on the audio to be played, and finally determining the start-stop time of each note in the music file based on the corrected start-stop time of each word and each note, so that the alignment of each tone of the audio to be played and each tone of the music file corresponding to the tone can be realized, the synchronism of the audio played tone and the tone of the music spectrum going to during the playing process is improved, the method is suitable for various plays, such as song speed change and the like, wherein, the correction mode can have different modes and can be freely combined, the flexibility is high, and for the application scene of the polyphonic melody, once one of the polyphonic melody has completed the spectrum and sound synchronization, other sound part melody can be directly applied based on the completed sound part melody, and the spectrum and sound synchronization is directly performed based on the completed sound part melody, so that the convenience and the efficiency of the spectrum and sound synchronization are greatly improved.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (15)
1. A method of spectral tone synchronization, comprising the steps of:
s1, determining the first start-stop time of each word in the singing lyrics of the audio to be played according to the audio to be played;
s2, acquiring a music score file corresponding to the audio to be played, and determining a second start-stop time of each word in the singing lyrics corresponding to the music score file according to the music score file and the first start-stop time;
and S3, determining the start-stop time of the corresponding note in the music score file according to the second start-stop time.
2. The spectrum tone synchronization method according to claim 1, wherein the S1 further comprises:
determining a third start-stop time of each note in the pure tone part of the audio to be played according to the audio to be played;
the S3 further includes:
and determining the fourth starting and stopping time of each note in the pure tone part corresponding to the music score file according to the music score file and the third starting and stopping time.
3. The method for synchronizing music score according to claim 1 or 2, wherein the determining the second start-stop time of each word of the singing lyrics corresponding to the music score file according to the music score file and the first start-stop time comprises:
expanding the singing lyrics corresponding to the music score file according to the time sequence according to the preset speed in the music score file;
and adjusting the singing lyrics corresponding to the music score file expanded according to the time sequence according to the first start-stop time of each word in the singing lyrics of the audio to be played to obtain the second start-stop time of each word in the singing lyrics corresponding to the music score file.
4. The spectrum tone synchronization method according to claim 2, wherein before determining the start-stop time of each note in the music score file in S3, the method further comprises:
and correcting target start-stop time according to the audio to be played, wherein the target start-stop time comprises at least one of the second start-stop time, the fourth start-stop time and start-stop time of corresponding notes determined by the second start-stop time.
5. The method for synchronizing spectrum tones according to claim 4, wherein said correcting the target start-stop time according to the audio to be played comprises:
converting the audio to be played into a waveform in a time domain;
determining a starting point and a terminating point of each target object of the audio to be played according to the waveform, wherein when the target starting and stopping time is a second starting and stopping time, the target object is a word in the lyrics to sing, and when the target starting and stopping time is a fourth starting and stopping time, the target object is a note in the pure tone part; when the target start-stop time is the start-stop time of the corresponding note determined by the second start-stop time, the target object is the corresponding note determined by the second start-stop time;
and correcting the target start-stop time corresponding to each target object according to the start point and the end point of each target object.
6. The method for synchronizing spectrum tones according to claim 5, wherein said determining a start point and an end point of each target object of the audio to be played according to the waveform comprises:
traversing each time point in the waveform in a time order, for the traversed time point:
judging whether the amplitude of the waveform is increased to be more than a first preset proportion of the maximum amplitude of the waveform within a first preset time from the time point, if so, the time point is the starting point of a target object;
if not, judging whether the amplitude of the waveform is reduced to be below a second preset proportion of the maximum amplitude of the waveform within a second preset time from the time point, if so, the time point is the end point of a target object;
otherwise, continuously traversing the next time point in the waveform until each time point in the waveform is traversed;
and determining the starting point and the ending point of each target object of the audio to be played according to the starting points and the ending points of all the target objects determined after the traversal is completed.
7. The method for synchronizing spectrum tones according to claim 4, wherein said correcting the target start-stop time according to the audio to be played comprises:
playing the audio to be played, performing voice recognition or tone recognition on the audio to be played, determining a starting point and a terminating point of each target object in the singing lyrics or the playing music of the audio to be played, wherein when the target starting and stopping time is a second starting and stopping time, the target object is a word in the singing lyrics, and when the target starting and stopping time is a fourth starting and stopping time, the target object is a note in the pure tone character part; when the target start-stop time is the start-stop time of the corresponding note determined by the second start-stop time, the target object is the corresponding note determined by the second start-stop time;
and correcting the target start-stop time corresponding to each target object according to the start point and the end point of each target object.
8. The method for synchronizing spectrum tones according to claim 4, wherein said correcting the target start-stop time according to the audio to be played comprises:
correspondingly displaying each target object of the audio to be played according to the target start-stop time and the playing sequence, wherein adjacent target objects are distinguished by different color blocks, the start-stop position of each color block on a time axis represents the start-stop time corresponding to each target object, the length of each color block on the time axis represents the time length corresponding to each target object, when the target start-stop time is the second start-stop time, the target objects are characters in the singing lyrics, and when the target start-stop time is the fourth start-stop time, the target objects are notes in the pure tone part; when the target start-stop time is the start-stop time of the corresponding note determined by the second start-stop time, the target object is the corresponding note determined by the second start-stop time;
playing the audio to be played, and synchronously displaying a progress bar on the color block in the playing process;
receiving an adjusting instruction sent by an operation object according to the deviation between the played audio and a target object indicated by the progress bar;
and correcting the target start-stop time according to the adjusting instruction.
9. The method according to claim 8, wherein the adjustment instruction includes a color block to be adjusted and an adjustment mode;
the correcting the target start-stop time according to the adjustment instruction comprises:
adjusting the starting and ending time boundary of the color block to be adjusted in the time axis direction according to the color block to be adjusted and the adjusting mode; or dragging the whole color block to be adjusted along the direction of a time axis;
and determining the target start-stop time according to the start-stop time boundary of the adjusted color block in the time axis direction.
10. A method for synchronizing spectrum sounds according to any one of claims 1, 2 and 4 to 9, wherein said determining the start-stop time of the corresponding note in the music score file according to the second start-stop time comprises:
and determining the start-stop time of the corresponding note in the music score file according to the corresponding relation between the lyrics and the note, the proportional relation between the note durations and the second start-stop time.
11. The method for synchronizing spectrum sounds according to claim 10, wherein the determining the start-stop time of each note in the music spectrum file according to the correspondence of the lyrics to the notes, the proportional relationship of the note durations and the second start-stop time comprises:
executing the following steps for each word in the audio to be played:
determining the number of notes corresponding to the words according to the corresponding relation between the lyrics and the notes;
if the number of the notes corresponding to the word is one, the start-stop time of the notes corresponding to the word is the second start-stop time corresponding to the word;
if the number of the notes corresponding to the word is more than two, determining the proportional relation of note duration values among the notes corresponding to the word;
and determining the start-stop time corresponding to each note corresponding to the word according to the proportional relation of the note duration and the second start-stop time corresponding to the word.
12. The spectrum tone synchronization method according to any one of claims 1, 2, 4 to 9 and 11, wherein said S3 further comprises:
judging whether the music score file contains a plurality of voice part music scores or not;
if yes, after the start-stop time of each corresponding note of one first sound part music score is determined, the start-stop time of each note corresponding to the rest sound part music scores is determined according to the corresponding relation between the rest sound part music scores and the notes of the first sound part music scores.
13. The method for synchronizing spectrum sounds according to claim 12, wherein said determining the start-stop time of each note corresponding to the rest of the vocal music score according to the correspondence between the rest of the vocal music score and the notes of the first vocal music score comprises:
judging whether the notes of the rest part music score and the notes of the first part music score are in one-to-one correspondence in the same time period and have the same note duration, if so, determining the start-stop time of each note of the rest part music score according to the start-stop time of each note of the first part music score in the same time period;
and if not, determining the start-stop time of each note of the rest part music score according to the proportional relation between the start-stop time and the note duration of each note of the first part music score and the note duration of each note of the rest part music score in the same time period.
14. The method according to claim 12 or 13, wherein it is determined whether the music score file contains a plurality of vocal parts music score and the vocal parts with independent lyrics exist except the first vocal part;
if so, after the start-stop time of each corresponding note of the qualified vocal part music score is determined, the start-stop time of each lyric of the qualified vocal part music score is determined according to the corresponding relation between each lyric of the qualified vocal part music score and the corresponding note of the qualified vocal part music score and the proportional relation between the start-stop time of each note of the qualified vocal part music score and the note time value.
15. A spectrum tone synchronization terminal comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the steps of a spectrum tone synchronization method according to any one of claims 1 to 14 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111259601.0A CN113870820A (en) | 2021-10-28 | 2021-10-28 | Spectrum and voice synchronization method and terminal |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111259601.0A CN113870820A (en) | 2021-10-28 | 2021-10-28 | Spectrum and voice synchronization method and terminal |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113870820A true CN113870820A (en) | 2021-12-31 |
Family
ID=78998667
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111259601.0A Pending CN113870820A (en) | 2021-10-28 | 2021-10-28 | Spectrum and voice synchronization method and terminal |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113870820A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116343720A (en) * | 2023-04-10 | 2023-06-27 | 广州感音科技有限公司 | Multi-sound part music score note grouping method, system, medium and computer |
| CN116504205A (en) * | 2023-03-01 | 2023-07-28 | 广州感音科技有限公司 | Musical performance control method, system, medium and computer |
-
2021
- 2021-10-28 CN CN202111259601.0A patent/CN113870820A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116504205A (en) * | 2023-03-01 | 2023-07-28 | 广州感音科技有限公司 | Musical performance control method, system, medium and computer |
| CN116504205B (en) * | 2023-03-01 | 2023-11-24 | 广州感音科技有限公司 | Musical performance control method, system, medium and computer |
| CN116343720A (en) * | 2023-04-10 | 2023-06-27 | 广州感音科技有限公司 | Multi-sound part music score note grouping method, system, medium and computer |
| CN116343720B (en) * | 2023-04-10 | 2023-11-21 | 广州感音科技有限公司 | Multi-sound part music score note grouping method, system, medium and computer |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10283099B2 (en) | Vocal processing with accompaniment music input | |
| CN105810190B (en) | Automatic transcription of music content and real-time musical accompaniment | |
| JP4353018B2 (en) | Musical instrument performance learning apparatus and program thereof | |
| US8802953B2 (en) | Scoring of free-form vocals for video game | |
| CN113870820A (en) | Spectrum and voice synchronization method and terminal | |
| CN109952609B (en) | Sound synthesizing method | |
| US20160210951A1 (en) | Automatic transcription of musical content and real-time musical accompaniment | |
| CN108630177B (en) | Electronic musical instrument, control method for electronic musical instrument, and recording medium | |
| US9147388B2 (en) | Automatic performance technique using audio waveform data | |
| US9286876B1 (en) | Method and apparatus for computer-aided variation of music and other sequences, including variation by chaotic mapping | |
| CN111048058B (en) | Singing or playing method and terminal for adjusting song music score in real time | |
| US20100175539A1 (en) | Automatic analysis and performance of music | |
| WO2016060211A1 (en) | Content control device and content control program | |
| US4999773A (en) | Technique for contouring amplitude of musical notes based on their relationship to the succeeding note | |
| JP5899833B2 (en) | Music generation apparatus and music generation method | |
| JP2008225117A (en) | Pitch display control device | |
| JP2004205817A (en) | Karaoke apparatus | |
| JP2016081045A (en) | Content control device and content control program | |
| JP4038836B2 (en) | Karaoke equipment | |
| US8158874B1 (en) | System and method for determining tempo in early music and for playing instruments in accordance with the same | |
| KR20010082407A (en) | Song accompaniment method to induce pitch correction. | |
| Clayton et al. | Rhythm and structural segmentation in Dhrupad Bandish performance | |
| JP5899832B2 (en) | Music generation apparatus and music generation method | |
| JP2018189735A (en) | Karaoke device | |
| JP3948425B2 (en) | Performance data processing apparatus and program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |