CN110246472A - A kind of conversion method of music style, device and terminal device - Google Patents
A kind of conversion method of music style, device and terminal device Download PDFInfo
- Publication number
- CN110246472A CN110246472A CN201910385803.6A CN201910385803A CN110246472A CN 110246472 A CN110246472 A CN 110246472A CN 201910385803 A CN201910385803 A CN 201910385803A CN 110246472 A CN110246472 A CN 110246472A
- Authority
- CN
- China
- Prior art keywords
- music
- coding
- mood
- mode
- target
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 39
- 230000036651 mood Effects 0.000 claims abstract description 116
- 238000013507 mapping Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 16
- 230000006978 adaptation Effects 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 17
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000013508 migration Methods 0.000 abstract description 7
- 230000005012 migration Effects 0.000 abstract description 7
- 230000000875 corresponding effect Effects 0.000 description 54
- 239000011295 pitch Substances 0.000 description 33
- 238000001514 detection method Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 3
- 230000013011 mating Effects 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000010422 painting Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
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
- G10H1/0033—Recording/reproducing or transmission of music for electrophonic musical instruments
- G10H1/0041—Recording/reproducing or transmission of music for electrophonic musical instruments in coded form
- G10H1/0058—Transmission between separate instruments or between individual components of a musical system
-
- 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
- G10H2210/00—Aspects or methods of musical processing having intrinsic musical character, i.e. involving musical theory or musical parameters or relying on musical knowledge, as applied in electrophonic musical tools or instruments
- G10H2210/325—Musical pitch modification
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Electrophonic Musical Instruments (AREA)
- Auxiliary Devices For Music (AREA)
Abstract
The present invention provides a kind of conversion method of music style, device and terminal devices, are suitable for technical field of data processing, this method comprises: obtaining the first musical instrument digital interface MIDI file about original audio data；The note element that the first MIDI file is included is parsed, and coded treatment is carried out by pitch value of the preset algorithm to note element, obtains the first coding；Obtain the coding mapping relation table of association original music mode and target music mood；Corresponding second coding of the first coding is determined based on coding mapping relation table, and processing is decoded to the second coding, to determine the pitch value of the second coding；The 2nd MIDI file of the pitch value about each second coding is generated, and target audio data are obtained according to the 2nd MIDI file.In the present invention, since user no longer needs to the music style for manually changing audio data according to the invention of oneself, it is thereby achieved that the automation of music style is converted, the flexibility and accuracy of music style migration are improved.
Description
Technical field
The invention belongs to technical field of data processing more particularly to a kind of conversion method of music style, device, terminal to set
Standby and computer readable storage medium.
Background technique
With the development of human material's civilization, spiritual civilization also starts to have obtained pay attention to day by day.It is prevailing in entertainment
In the epoch, the technology of music field plays particularly important effect to contemporary spiritual civilization construction, and music style migrates always all
It is a big rigid demand in music music field.Music style migrating technology can provide for all kinds of entertainment medias, singer or composer etc.
It easily supports very much, such as: when playing the video image of the more sad painting style, the music style of the more droning sorrow of use
Carry out music；When playing more celebrating video image, then switch the music style progress music for choosing more cheerful and light-hearted happiness.
However, usually, the migration of melody music style is all to be set up by user according to the invention of oneself
At, accordingly, it is difficult to realize the automation migration of music style, there is lower flexibility.
Summary of the invention
In view of this, the embodiment of the invention provides a kind of conversion method of music style, device, terminal device and calculating
Machine readable storage medium storing program for executing was migrated with solving the automation migration for being difficult to realize music style in the prior art and music style
The lower problem of flexibility in the presence of journey.
The first aspect of the embodiment of the present invention provides a kind of conversion method of music style, comprising:
Obtain the first musical instrument digital interface MIDI file about original audio data；
The note element that the first MIDI file is included is parsed, and by preset algorithm to the sound of the note element
High level carries out coded treatment, obtains the first coding；
Obtain the coding mapping relation table of association original music mode and target music mood；
Corresponding second coding of first coding is determined based on the coding mapping relation table, and to second coding
It is decoded processing, with the pitch value of determination second coding；
The 2nd MIDI file of the pitch value about each second coding is generated, and according to the 2nd MIDI file
Obtain target audio data.
The second aspect of the embodiment of the present invention provides a kind of conversion equipment of music style, comprising:
First acquisition unit, for obtaining the first musical instrument digital interface MIDI file about original audio data；
Resolution unit, the note element for being included for parsing the first MIDI file, and by preset algorithm to institute
The pitch value for stating note element carries out coded treatment, obtains the first coding；
Second acquisition unit, for obtaining the coding mapping relationship of association original music mode and target music mood
Table；
Decoding unit, for determining corresponding second coding of first coding based on the coding mapping relation table, and
Processing is decoded to second coding, with the pitch value of determination second coding；
Generation unit, for generating the 2nd MIDI file of the pitch value about each second coding, and according to institute
It states the 2nd MIDI file and obtains target audio data.
The third aspect of the embodiment of the present invention provides a kind of terminal device, including memory and processor, described to deposit
Reservoir is stored with the computer program that can be run on the processor, and the processor is realized when executing the computer program
The step of such as conversion method of above-mentioned music mood.
The fourth aspect of the embodiment of the present invention provides a kind of computer readable storage medium, the computer-readable storage
Media storage has computer program, and the processor realizes the conversion side such as above-mentioned music mood when executing the computer program
The step of method.
In the embodiment of the present invention, by obtaining the musical instrument digital interface MIDI file about original audio data, so that being
System can parse digitized MIDI file, to determine each note element and sound that original audio data is included
Happy mode, to realize the encoding operation to note element.By pre-establishing about correlation between all kinds of music moods
Coding mapping relation table so that each music in target music mood can be automatically determined when knowing target music mood
The pitch value of element generates the target MIDI file about wherein each pitch value, realizes the automation conversion of music style.?
During being somebody's turn to do, since user no longer needs to the music style for manually changing audio data according to the invention of oneself, mention
The high flexibility and accuracy of music style migration.
Detailed description of the invention
It to describe the technical solutions in the embodiments of the present invention more clearly, below will be to embodiment or description of the prior art
Needed in attached drawing be briefly described, it should be apparent that, the accompanying drawings in the following description is only of the invention some
Embodiment for those of ordinary skill in the art without any creative labor, can also be according to these
Attached drawing obtains other attached drawings.
Fig. 1 is the implementation process schematic diagram of the conversion method of music style provided in an embodiment of the present invention；
Fig. 2 be another embodiment of the present invention provides music style conversion method implementation process schematic diagram；
Fig. 3 is the implementation process schematic diagram of the conversion method for the music style that further embodiment of this invention provides；
Fig. 4 is the implementation process schematic diagram of the conversion method for the music style that further embodiment of this invention provides；
Fig. 5 is the specific implementation flow chart of the conversion method S114 of music style provided in an embodiment of the present invention；
Fig. 6 is the structural block diagram of the conversion equipment of music style provided in an embodiment of the present invention；
Fig. 7 is the schematic diagram of terminal device provided in an embodiment of the present invention.
Specific embodiment
In being described below, for illustration and not for limitation, the tool of such as particular system structure, technology etc is proposed
Body details, to understand thoroughly the embodiment of the present invention.However, it will be clear to one skilled in the art that there is no these specific
The present invention also may be implemented in the other embodiments of details.In other situations, it omits to well-known system, device, electricity
The detailed description of road and method, in case unnecessary details interferes description of the invention.
It should be understood that although term " first ", " second " etc. are used in some embodiment of the present invention in the text
Various elements are described, but these elements should not be limited by these terms.These terms are used only to an element
It is distinguished with another element.For example, the first coding can be named as the second coding, and similarly, the second coding can be by
It is named as the first coding, without departing from the range of various described embodiments.First coding and the second coding are all codings, but
It is them is not same type of coding.
In order to illustrate technical solutions according to the invention, the following is a description of specific embodiments.
Fig. 1 shows the implementation flow chart of the conversion method of music style provided in an embodiment of the present invention, and details are as follows:
S101: the first musical instrument digital interface MIDI file about original audio data is obtained.
In the embodiment of the present invention, need to be implemented the snatch of music that music style is converted into original audio data, in particular to
The speech simulation signal of the musical sound type acquired in advance.Obtain the pleasure about the original audio data in the following manner
Device digital interface (Musical Instrument Digital Interface, MIDI) file: to above sound analog signal
It sampled, quantified and is encoded, obtain the MIDI file about original audio data；Alternatively, passing through MIDI keyboard or device of setting the chessman on the chessboard according to the chess manual
Equal tools obtain the MIDI file about original audio data, comprising: if detecting, musical composition people triggers each happy key,
According to the trigger sequence of each happy key, corresponding single melody MIDI file is generated；By MIDI keyboard or set the chessman on the chessboard according to the chess manual provided by device
Mating interface receives its MIDI file transmitted.
In the embodiment of the present invention, the different musical sound of several height, around a certain middle heart sound for having sense of stability, by certain
It is music mood that interval relation, which organizes together and is formed by an organic system,.Different music moods has different sounds
Correlation between stage structure and sound level, so that different melodies can have different style characteristics.
The music mood of original audio data is original music mode.In the embodiment of the present invention, to original audio data
Before carrying out music style conversion, the music mood of the original audio data is obtained, comprising: record the ginseng of input in advance according to user
Number information extracts the music mood about the original audio data from parameter information；Alternatively, passing through detection original audio data
In each note element musical alphabet, determine the music mood of original audio data.Wherein, music mood includes but is not limited to 20
Four big ditties, Chinese tradition Pentatonic and Japan all save mode etc..
It illustratively, only include this five musical alphabets of C, D, E, G, A in original audio data if detecting, it is determined that its is original
Music mood is Chinese tradition Pentatonic.
S102: the note element that parsing the first MIDI file is included, and by preset algorithm to the note member
The pitch value of element carries out coded treatment, obtains the first coding.
In the embodiment of the present invention, the MIDI file about original audio data is traversed by preset algorithm, to detect its packet
The pitch value of each note element contained, and in the array that the deposit of each pitch value is pre-established.Wherein, the sound of note element
High level indicates its MIDI pitch.Above-mentioned preset algorithm is used for the corresponding relationship according to note element and MIDI pitch, exports MIDI
The corresponding MIDI pitch of each note element in file.For example, if preset algorithm may is that for i in midi:pitches
=i.pitch；Then for note Elements C 4, D4, E4, F4, G4, after being inputted the preset algorithm, correspondence can be exported respectively
MIDI pitch be 60,62,64,65,67.
In the embodiment of the present invention, according to preset encryption algorithm, the MIDI pitch in array is handled, to generate
One coding.Illustratively, each note element for being 60,62,64,65,67 for MIDI pitch, with the numerical value 12 of 12 equal temperances
For modulus value, by modulus algorithm, exportable corresponding each first is encoded to ac、bc、cc、dc、ec.Modulus algorithm for example can be with
It is: for arr [i] in arr:if mod (arr [i], 12)=0new_arr.push (ac) | if mod (arr [i], 12)=
2new_arr.push(bc) | if mod (arr [i], 12)=4new_arr.push (cc) | if mod (arr [i], 12)=
7new_arr.push(dc) | if mod (arr [i], 12)=9new_arr.push (ec).Wherein, arr is coded sequence, and i is
The index of pitch sequence, i.e. the MIDI pitch of some note element, new_arr are the newly encoded sequence of output.
S103: the coding mapping relation table of association original music mode and target music mood is obtained.
Target music mood is wanted the music wind that the music style type obtained or current application scene are adapted to by user
Lattice type.For example, if the original music mode of audio data is Chinese tradition Pentatonic, and user wants Chinese tradition five
The section audio data of tone formula are converted to the audio data that Japan all saves mode, then the target music mood at current time is
Japan all saves mode.
Target music mood can choose instruction according to mode that user is issued in terminal interface to determine, can also be by
System is chosen automatically.
The mode of target music mood is determined to instruction is chosen based on mode, specifically, is executing turning for music mood
It changes before operation, in terminal interface, shows one or more display controls.Each display control is used to identify and can be selected
One music mood.If the selection for detecting that user issues any display control instructs, which is identified
Music mood is determined as target music mood.
Preferably, if the target music mood detected automatically chooses the determined target music of instruction with according to mode
Mode is different, then obtains priority corresponding to each detection mode, and chooses the detection mode institute of wherein highest priority
The music mood matched is as target music mood.
Preferably, the detection mode of target music mood is determined to instruction is chosen based on mode, default priority is
Highest priority.
Preferably, priority corresponding to above-mentioned all kinds of detection modes sets the parameters to determine according to preparatory typing.
In the embodiment of the present invention, coding mapping relation table describes the one-to-one correspondence between different music mood note elements
Relationship, the coding mapping relationship between different music moods construct in advance according to music theory knowledge.For example, in c major, if sound
A is encoded to corresponding to symbol Elements Cc, and need to be converted to the original audio data of c major the target audio data of the big tune of G,
Then with coding acCoding with mapping relations will be redefined for ec, and encode ecIt is corresponding with note element G.
Illustratively, mode is all saved with Japan and can be with the associated coding mapping relation table of Chinese tradition Pentatonic
Are as follows: ac→ar；bc→br；cc→cr；dc→dr；ec→er。
The target music mood and original music mode detected according to current time, in pre-stored multiple volumes
In code mapping table, determine and the target music mood and the matched coding mapping relation table of original music mode.
S104: corresponding second coding of first coding is determined based on the coding mapping relation table, and to described the
Two codings are decoded processing, with the pitch value of determination second coding.
To generated in above-mentioned S103 each first coding, in the coding mapping relation table determined, search with
Corresponding second coding of first coding.By the inclusion of the preset algorithm of the second coding and MIDI pitch matching relationship, output
The wherein MIDI pitch of each the second coding.
S105: the 2nd MIDI file of the pitch value about each second coding is generated, and according to described second
MIDI file obtains target audio data.
For the first MIDI file of original audio data, in its channel sound information, each note element is read
Note-On note opens information and Note-Off note closes information.Note-On note opens information and Note-Off note closes letter
The start/stop time for marking note element is ceased, so as to open information and Note-Off note pass letter based on Note-On note
Breath, determines the duration of each note element.In the embodiment of the present invention, the corresponding note element of the first coding of record
Note-On note opens information and Note-Off note closes information.The second coding corresponding for first coding, by this
Note-On note opens information and Note-Off note closes note element binding corresponding to information and second coding.At this point,
Since the MIDI pitch and note duration of the corresponding note element of the second coding can determine, according to each
Second coding puts in order, and the music element of respective corresponding output is sequentially written in new the 2nd MIDI text currently created
In part.
By playing out to the 2nd MIDI file of output, enable the music style of original audio data from original
Music mood is converted to target music mood.
In the embodiment of the present invention, by obtaining the musical instrument digital interface MIDI file about original audio data, so that being
System can parse digitized MIDI file, to determine each note element and sound that original audio data is included
Happy mode, to realize the encoding operation to note element.By pre-establishing about correlation between all kinds of music moods
Coding mapping relation table so that each music in target music mood can be automatically determined when knowing target music mood
The pitch value of element generates the target MIDI file about wherein each pitch value, to realize the automation conversion of music style.
In the process, since user no longer needs to the music style for manually changing audio data according to the invention of oneself, it mentions
The high flexibility and accuracy of music style migration.
As another embodiment of the invention, on the basis of above-described embodiment, target sound is automatically determined to system
The mode of happy mode is further limited.As shown in Fig. 2, before above-mentioned S103, further includes:
S106: the scene types of adaptations at current time is determined；The scene types of adaptations is for describing target audio data
Application scenarios.
In the embodiment of the present invention, scene types of adaptations of the current time about target audio data is detected, scene is adapted to class
Type includes but is not limited to the preset kinds such as video display, speech, outdoor sports and sleep.Scene types of adaptations is inputted by user
Set the parameters to determine.
S107: if the scene types of adaptations is video display, the video image frame played in real time is obtained.
S108: the characteristic information that the video image frame is included is obtained.
S109: if the characteristic information matches with the characteristic information in any the presets list, by described the presets list
Corresponding music mood is determined as the target music mood at current time.
If detecting, the scene types of adaptations at current time is video display, then it represents that target audio data application is in magic lantern
Among the scene that piece plays or image plays.By preset video display platform mating interface, obtained in real time in broadcasting
The video image frame of state, and it is based on image recognition algorithm, determine the various features information that current video image frame is included.It is special
Reference breath includes semantic information and object type etc..
In the embodiment of the present invention, load and the matched multiple the presets lists of each music mood.Each the presets list record
There is multinomial characteristic information relevant to scene type.For example, may include having football, basketball, running and movement in the presets list
The characteristic information relevant to sport such as clothing.
If detected characteristic information is matched with the characteristic information in any the presets list in current video image frame,
By the presets list matched music mood be determined as the target music mood at current time.
Illustratively, if in current video image frame including text informations such as " happy new year ", and such red-letter day feature
Information is present in the presets list 1, then is determined as currently needing to original audio number by the 1 matched music mood of institute of the presets list
According to obtained target music mood after progress music style conversion.At this point, the 1 matched music mood of institute of the presets list can be pre-
It is set as more cheerful and more light-hearted music mood, such as all kinds of big tune formulas.
As another embodiment of the invention, in above-mentioned S109, if detecting spy included in video image frame
Reference breath included with any the presets list characteristic information match, and music mood corresponding to the presets list for two with
On, then as shown in figure 3, after above-mentioned S109, further includes:
S110: the historical usage number of each music mood corresponding to described the presets list is obtained respectively.
In the embodiment of the present invention, every time when music mood corresponding to the presets list is determined as target music mood,
The historical usage number of the music mood is executed plus one is handled, and processing result is stored to tables of data.
To the video image frame that above-mentioned S109 is detected, if characteristic information included in the video image frame with appoint
The characteristic information matching that one the presets list is included reads each sound corresponding with the presets list then from above-mentioned tables of data
The historical usage number of happy mode.
S111: target music tune of the least music mood of the historical usage number as current time is chosen
Formula, and real-time monitoring is carried out to the video image frame.
By comparing the numerical values recited of the historical usage number of each music mood, it is least to select historical usage number
Target music mood of the music mood as current time.Wherein, if the least music mood of historical usage number is two
More than a, then a music mood is therefrom randomly selected as target music mood.
After determining the target music mood at current time, video image frame that persistently video display platform is played into
Row monitoring, to determine whether current video image frame changes relative to a upper video image frame.
S112: it if the characteristic information for monitoring that the video image frame is included changes, and changes amplitude and is less than in advance
If threshold value, then target music tune of the least music mood of the historical usage number as current time is persistently applied
Formula.
S113: if monitoring, the change amplitude of the characteristic information is greater than or equal to preset threshold, reacquires and becomes
Music mood corresponding to the presets list is then updated to current time by the presets list that the characteristic information after more matches
Target music mood.
In the embodiment of the present invention, if monitoring, current video image frame is changed relative to a upper video image frame,
Obtain the characteristic information that current video image frame is included.By preset image alignment algorithm, calculate current characteristic information with
The change amplitude for the characteristic information that a upper video image frame is included.If the amplitude of change is less than preset threshold, then follow the steps
The holding of music mood determined by previous moment is chosen to be target music mood by S112；If the amplitude of change is greater than or equal to pre-
If threshold value then returns to step S109, to judge the matched the presets list of characteristic information institute at current time, and this is preset
Music mood corresponding to list is updated to the target music mood at current time.
The step realization principle that do not mention in the embodiment of the present invention is identical as the step realization principle of remaining each embodiment,
Therefore it no longer repeats one by one.
It is view in scene types of adaptations by determining the scene types of adaptations of target audio data in the embodiment of the present invention
In the case that frequency is demonstrated, the default column that all kinds of music moods are corresponded to come Auto-matching are detected according to the feature to video image frame
Table, and music mood corresponding to the presets list that matching is obtained realizes target music mood as target music mood
Automation selection, ensure that user without by hand choose target music mood, reduce operation complexity and cumbersome degree；It is logical
The change amplitude for crossing the characteristic information that detection video image frame is included persistently applies original mesh when the amplitude of change is smaller
Music mood is marked, the music style that background system needs continuously to change audio data is avoided, improves target audio
The broadcasting continuity of data, thus also reduces the consumption of system operations resource；By redefining when the amplitude of change is larger
The target music mood at current time, ensure that target music mood and practical application scene can matching degree with higher,
To improve the applicability of target audio data.
As one more embodiment of the present invention, Fig. 4 shows the conversion method of music style provided in an embodiment of the present invention
Implementation process.As shown in figure 4, further including step S114 before above-mentioned S103, the first MIDI file is identified
Processing, with the original music mode of the determination original audio data.
Wherein, step S114 includes S1141 to S1144.The realization principle of each step is specific as follows:
S1141: the note element that parsing the first MIDI file is included, and generate and be based on each note element
The first scale sequence.
In the embodiment of the present invention, the first MIDI file of the parsing music element that is included, that is, determine it includes each sound
Happy element is which of 12 sound ranks note.12 sound ranks include C, C#, D, D#, E, F, F#, G, G#, A, A# and
B。
According to the MIDI pitch of each music element parsed, each music element is ranked up, to obtain first
Scale sequence.Wherein, the music element repeated is not included in the first scale sequence.
S1142: the second scale sequence corresponding to each preset musical mode is obtained respectively.
According to music theory knowledge it is found that each preset musical mode has corresponding scale, therefore, in the embodiment of the present invention,
Based on the setting instruction being previously received, obtains and store the second scale sequence corresponding to each preset musical mode.Such as:
Second scale sequence corresponding to c major are as follows: { C D E F G A B C }, the second scale sequence corresponding to the big tune of E are as follows: { E
F#G#A B C#D#E}。
S1143: the similarity by comparing the first scale sequence and each second scale sequence calculates separately
The statistics score of the preset musical mode corresponding to each second scale sequence.
The first scale sequence and second sound are calculated by preset algorithm to each pre-stored second scale sequence
The similarity of rank sequence, and it is based on the similarity, calculate counting for preset musical mode corresponding to the second scale sequence
Point.Wherein, statistics score is used to indicate the matching degree of the first scale sequence and preset musical mode, and statistics score to it is similar
Degree is positively correlated.
Optionally, in order to reduce computational complexity, the similarity of above-mentioned first scale sequence and the second scale sequence is straight
Connect the statistics score that output is preset musical mode corresponding with the second scale sequence.
Optionally, above by preset algorithm, the similarity of the first scale sequence and the second scale sequence, packet are calculated
It includes: generating and the corresponding primary vector of the first scale sequence and secondary vector corresponding with the second scale sequence respectively；It calculates
The cosine similarity of primary vector and secondary vector；It is the first scale sequence and the second scale sequence by cosine similarity output
The similarity of column.
S1144: the preset musical mode of the statistics highest scoring is determined as the original music mode.
In the embodiment of the present invention, after the statistics score that each preset musical mode is calculated separately by above-mentioned S1143, screening
The preset musical mode of highest scoring is counted out, then the default mode is the original music mode of original audio data.
Preferably as one embodiment of the present of invention, Fig. 5 shows turning for music style provided in an embodiment of the present invention
The specific implementation flow of method S1143 is changed, details are as follows:
S11431: to each second scale sequence, by comparing the first scale sequence and the second scale sequence
The similarity of column calculates the first score value of the preset musical mode corresponding with the second scale sequence.
In the embodiment of the present invention, by preset algorithm, the similarity of the first scale sequence and the second scale sequence is calculated,
And the incidence relation based on the similarity Yu the first score value, determine of preset musical mode corresponding to the second scale sequence
One score value.
Wherein, the incidence relation of similarity and the first score value can be specific function relationship.At this point, by that will be calculated
The first scale sequence and the second scale sequence input parameter of the similarity as above-mentioned specific function, it is exportable corresponding
Second score value.
S11432: the keynote element of the second scale sequence is obtained.
According to music theory knowledge, each music mood all has its corresponding keynote element.Keynote element is a music
Most stable of sound in the core of mode and the music mood.For each preset musical mode, by its second music sequence
In first note element be read as keynote element.
S11433: in the first scale sequence, the first of first note element and the keynote element is calculated separately
Matching degree and the second matching degree for calculating tail portion note element and the keynote element.
In the embodiment of the present invention, the master of the first element and every one second scale sequence in the first scale sequence is calculated separately
First matching degree of tone element.Illustratively, if the keynote of first element and one second scale sequence in the first scale sequence
Element is identical, then first matching degree of the two is 1；If the master of first element and one second scale sequence in the first scale sequence
Tone element is different, then first matching degree of the two is 0.
Similarly, the keynote element of the tail portion note element and every one second scale sequence in the first scale sequence is calculated separately
The second matching degree.
S11434: it according to first matching degree and second matching degree, calculates corresponding with the second scale sequence
Second score value of the preset musical mode, and it is based on first score value and second score value, it calculates and second sound
The statistics score of the corresponding preset musical mode of rank sequence.
To the first matching degree and the second matching degree associated by every one second scale sequence, by preset algorithm to this
One matching degree and the second matching degree carry out integration operation, obtain of preset musical mode corresponding to the second scale sequence
Two score values.
In the embodiment of the present invention, the first score value and the second score value based on each preset musical mode calculate default sound
The statistics score of happy mode.Calculation includes but is not limited to sum operation, ranking operation and all kinds of logical algorithm operations etc..
It is former under the music mood of original audio data and the matched situation of preset musical mode in the embodiment of the present invention
Each music element that beginning audio data is included can be contained in scale sequence corresponding to preset musical mode, in big portion
It is consistent in the case of point with music theory music principle, therefore, the first scale sequence and default sound by the first MIDI file of generation
Second scale sequence of happy mode compares the similarity of the two to determine the statistics score of preset musical mode, and will count
Point highest preset musical mode is identified as the original music mode of original audio data, realize to original music mode from
Dynamicization detection, improves the intellectualized detection degree of music mood；Since the starting sound and ending sound of original audio data are usual
Also it therefore can be matched by calculating first note element with the first of keynote element with the keynote Match of elemental composition of its music mood
Degree and the second matching degree for calculating tail portion note element and keynote element, the considerations of polymorphic type can be integrated the factor it is pre- to calculate
If the statistics score of music mood, thus also improve the Detection accuracy to original music mode.
It should be understood that the size of the serial number of each step is not meant that the order of the execution order in above-described embodiment, each process
Execution sequence should be determined by its function and internal logic, the implementation process without coping with the embodiment of the present invention constitutes any limit
It is fixed.
Corresponding to the method for foregoing embodiments, Fig. 6 shows the conversion equipment of music style provided in an embodiment of the present invention
Structural block diagram, for ease of description, only parts related to embodiments of the present invention are shown.The exemplary music style of Fig. 6
Conversion equipment can be the executing subject of the conversion method of the music style of previous embodiment offer.
Referring to Fig. 6, the conversion equipment of the music style includes:
First acquisition unit 61, for obtaining the first musical instrument digital interface MIDI file about original audio data.
Resolution unit 62, the note element for being included for parsing the first MIDI file, and pass through preset algorithm pair
The pitch value of the note element carries out coded treatment, obtains the first coding.
Second acquisition unit 63, for obtaining the coding mapping relationship of association original music mode and target music mood
Table.
Decoding unit 64, for determining corresponding second coding of first coding based on the coding mapping relation table,
And processing is decoded to second coding, with the pitch value of determination second coding.
Generation unit 65, for generate about it is each it is described second coding pitch value the 2nd MIDI file, and according to
The 2nd MIDI file obtains target audio data.
Optionally, the conversion equipment of the music style further include:
First determination unit, for determining the scene types of adaptations at current time；The scene types of adaptations is for describing
The application scenarios of target audio data.
Third acquiring unit obtains the video figure played in real time if being video display for the scene types of adaptations
As frame.
4th acquiring unit, the characteristic information for being included for obtaining the video image frame.
Second determination unit will if matching for the characteristic information and the characteristic information in any the presets list
Music mood corresponding to described the presets list is determined as the target music mood at current time.
Optionally, if music mood corresponding to described the presets list is two or more, the conversion of the music style
Device further include:
5th acquiring unit, the history for obtaining each music mood corresponding to described the presets list respectively are answered
Use number.
Monitoring unit, for choosing target of the least music mood of the historical usage number as current time
Music mood, and real-time monitoring is carried out to the video image frame.
Constant cell if the characteristic information for monitoring that the video image frame is included changes, and changes width
Degree is less than preset threshold, then persistently applies target of the least music mood of the historical usage number as current time
Music mood.
Updating unit, if for monitoring that the change amplitude of the characteristic information is greater than or equal to preset threshold, again
The presets list to match with the characteristic information after change is obtained, then is updated to work as by music mood corresponding to the presets list
The target music mood at preceding moment.
Optionally, the conversion equipment of the music style further include:
Recognition unit, for carrying out identifying processing to the first MIDI file, with the determination original audio data
Original music mode.
Optionally, the recognition unit includes:
Parsing subunit, the note element for being included for parsing the first MIDI file, and generate and be based on each institute
State the first scale sequence of note element；
Subelement is obtained, for obtaining the second scale sequence corresponding to each preset musical mode respectively；
Computation subunit, for similar to each second scale sequence by comparing the first scale sequence
Degree, calculates separately the statistics score of the preset musical mode corresponding to each second scale sequence；
Subelement is determined, for the preset musical mode of the statistics highest scoring to be determined as the original music
Mode.
Optionally, the computation subunit is specifically used for:
It is similar to the second scale sequence by comparing the first scale sequence to each second scale sequence
Degree calculates the first score value of the preset musical mode corresponding with the second scale sequence；
Obtain the keynote element of the second scale sequence；
In the first scale sequence, calculate separately the first matching degree of first note element and the keynote element with
And calculate the second matching degree of tail portion note element and the keynote element；
According to first matching degree and second matching degree, calculate corresponding with the second scale sequence described default
Second score value of music mood, and it is based on first score value and second score value, it calculates and the second scale sequence pair
The statistics score for the preset musical mode answered.
In the embodiment of the present invention, by obtaining the musical instrument digital interface MIDI file about original audio data, so that being
System can parse digitized MIDI file, to determine each note element and sound that original audio data is included
Happy mode, to realize the encoding operation to note element.By pre-establishing about correlation between all kinds of music moods
Coding mapping relation table so that each music in target music mood can be automatically determined when knowing target music mood
The pitch value of element generates the target MIDI file about wherein each pitch value, to realize the automation conversion of music style.
In the process, since user no longer needs to the music style for manually changing audio data according to the invention of oneself, it mentions
The high flexibility and accuracy of music style migration.
Fig. 7 is the schematic diagram for the terminal device that one embodiment of the invention provides.As shown in fig. 7, the terminal of the embodiment is set
Standby 7 include: processor 70 and memory 71, and the calculating that can be run on the processor 70 is stored in the memory 71
Machine program 72.The processor 70 realizes that the conversion method of above-mentioned each music style is implemented when executing the computer program 72
Step in example, such as step 101 shown in FIG. 1 is to 105.Alternatively, when the processor 70 executes the computer program 72
Realize the function of each module/unit in above-mentioned each Installation practice, such as the function of unit 61 to 65 shown in Fig. 6.
The terminal device 7 can be the calculating such as desktop PC, notebook, palm PC and cloud server and set
It is standby.The terminal device may include, but be not limited only to, processor 70, memory 71.It will be understood by those skilled in the art that Fig. 7
The only example of terminal device 7 does not constitute the restriction to terminal device 7, may include than illustrating more or fewer portions
Part perhaps combines certain components or different components, such as the terminal device can also include input sending device, net
Network access device, bus etc..
Alleged processor 70 can be central processing unit (Central Processing Unit, CPU), can also be
Other general processors, digital signal processor (Digital Signal Processor, DSP), specific integrated circuit
(Application Specific Integrated Circuit, ASIC), ready-made programmable gate array (Field-
Programmable Gate Array, FPGA) either other programmable logic device, discrete gate or transistor logic,
Discrete hardware components etc..General processor can be microprocessor or the processor is also possible to any conventional processor
Deng.
The memory 71 can be the internal storage unit of the terminal device 7, such as the hard disk or interior of terminal device 7
It deposits.The memory 71 is also possible to the External memory equipment of the terminal device 7, such as be equipped on the terminal device 7
Plug-in type hard disk, intelligent memory card (Smart Media Card, SMC), secure digital (Secure Digital, SD) card dodge
Deposit card (Flash Card) etc..Further, the memory 71 can also both include the storage inside list of the terminal device 7
Member also includes External memory equipment.The memory 71 is for storing needed for the computer program and the terminal device
Other programs and data.The memory 71, which can be also used for temporarily storing, have been sent or data to be sent.
It, can also be in addition, the functional units in various embodiments of the present invention may be integrated into one processing unit
It is that each unit physically exists alone, can also be integrated in one unit with two or more units.Above-mentioned integrated list
Member both can take the form of hardware realization, can also realize in the form of software functional units.
If the integrated module/unit be realized in the form of SFU software functional unit and as independent product sale or
In use, can store in a computer readable storage medium.Based on this understanding, the present invention realizes above-mentioned implementation
All or part of the process in example method, can also instruct relevant hardware to complete, the meter by computer program
Calculation machine program can be stored in a computer readable storage medium, the computer program when being executed by processor, it can be achieved that on
The step of stating each embodiment of the method.Wherein, the computer program includes computer program code, the computer program generation
Code can be source code form, object identification code form, executable file or certain intermediate forms etc..The computer-readable medium
It may include: any entity or device, recording medium, USB flash disk, mobile hard disk, magnetic that can carry the computer program code
Dish, CD, computer storage, read-only memory (Read-Only Memory, ROM), random access memory (Random
Access Memory, RAM), electric carrier signal, telecommunication signal and software distribution medium etc..
Embodiment described above is merely illustrative of the technical solution of the present invention, rather than its limitations；Although referring to aforementioned reality
Applying example, invention is explained in detail, those skilled in the art should understand that: it still can be to aforementioned each
Technical solution documented by embodiment is modified or equivalent replacement of some of the technical features；And these are modified
Or replacement, the essence of corresponding technical solution is departed from the spirit and scope of the technical scheme of various embodiments of the present invention, it should all
It is included within protection scope of the present invention.
Claims (10)
1. a kind of conversion method of music mood characterized by comprising
Obtain the first musical instrument digital interface MIDI file about original audio data；
The note element that the first MIDI file is included is parsed, and by preset algorithm to the pitch value of the note element
Coded treatment is carried out, the first coding is obtained；
Obtain the coding mapping relation table of association original music mode and target music mood；
Corresponding second coding of first coding is determined based on the coding mapping relation table, and second coding is carried out
Decoding process, with the pitch value of determination second coding；
The 2nd MIDI file of the pitch value about each second coding is generated, and is obtained according to the 2nd MIDI file
Target audio data.
2. the conversion method of music mood as described in claim 1, which is characterized in that be associated with original music tune in the acquisition
Before the coding mapping relation table of formula and target music mood, further includes:
Determine the scene types of adaptations at current time；The scene types of adaptations is used to describe the applied field of target audio data
Scape；
If the scene types of adaptations is video display, the video image frame played in real time is obtained；
Obtain the characteristic information that the video image frame is included；
If the characteristic information matches with the characteristic information in any the presets list, by sound corresponding to described the presets list
Happy mode is determined as the target music mood at current time.
3. the conversion method of music mood as claimed in claim 2, which is characterized in that if sound corresponding to described the presets list
Happy mode is two or more, then the conversion method of the music mood includes:
The historical usage number of each music mood corresponding to described the presets list is obtained respectively；
Target music mood of the least music mood of the historical usage number as current time is chosen, and to described
Video image frame carries out real-time monitoring；
If the characteristic information for monitoring that the video image frame is included changes, and changes amplitude and be less than preset threshold, then
Persistently target music mood of the application least music mood of the historical usage number as current time；
If monitoring, the change amplitude of the characteristic information is greater than or equal to preset threshold, reacquires and the feature after change
Music mood corresponding to the presets list is then updated to the target music tune at current time by the presets list that information matches
Formula.
4. the conversion method of music mood as described in claim 1, which is characterized in that be associated with original music tune in the acquisition
Before the coding mapping relation table of formula and target music mood, further includes:
Identifying processing is carried out to the first MIDI file, with the original music mode of the determination original audio data.
5. the conversion method of music mood as claimed in claim 4, which is characterized in that it is described to the first MIDI file into
Row identifying processing, with the original music mode of the determination original audio data, comprising:
The note element that the first MIDI file is included is parsed, and generates the first scale based on each note element
Sequence；
The second scale sequence corresponding to each preset musical mode is obtained respectively；
By comparing the similarity of the first scale sequence and each second scale sequence, each described the is calculated separately
The statistics score of the preset musical mode corresponding to two scale sequences；
The preset musical mode of the statistics highest scoring is determined as the original music mode.
6. the conversion method of music style as claimed in claim 5, which is characterized in that described by comparing first scale
The similarity of sequence and each second scale sequence calculates separately described pre- corresponding to each second scale sequence
If the statistics score of music mood, comprising:
To each second scale sequence, by comparing the similarity of the first scale sequence and the second scale sequence,
Calculate the first score value of the preset musical mode corresponding with the second scale sequence；
Obtain the keynote element of the second scale sequence；
In the first scale sequence, the first matching degree and meter of first note element Yu the keynote element are calculated separately
Calculate the second matching degree of tail portion note element and the keynote element；
According to first matching degree and second matching degree, the preset musical corresponding with the second scale sequence is calculated
Second score value of mode, and it is based on first score value and second score value, it calculates corresponding with the second scale sequence
The statistics score of the preset musical mode.
7. a kind of conversion equipment of music style characterized by comprising
First acquisition unit, for obtaining the first musical instrument digital interface MIDI file about original audio data；
Resolution unit, the note element for being included for parsing the first MIDI file, and by preset algorithm to the sound
The pitch value of symbol element carries out coded treatment, obtains the first coding；
Second acquisition unit, for obtaining the coding mapping relation table of association original music mode and target music mood；
Decoding unit, for determining corresponding second coding of first coding based on the coding mapping relation table, and to institute
It states the second coding and is decoded processing, with the pitch value of determination second coding；
Generation unit, for generating the 2nd MIDI file of the pitch value about each second coding, and according to described the
Two MIDI files obtain target audio data.
8. the conversion equipment of music style as claimed in claim 7, which is characterized in that further include:
First determination unit, for determining the scene types of adaptations at current time；The scene types of adaptations is for describing target
The application scenarios of audio data；
Third acquiring unit obtains the video image frame played in real time if being video display for the scene types of adaptations；
4th acquiring unit, the characteristic information for being included for obtaining the video image frame；
Second determination unit will be described if matching for the characteristic information and the characteristic information in any the presets list
Music mood corresponding to the presets list is determined as the target music mood at current time.
9. a kind of terminal device, including memory and processor, the memory, which is stored with, to be run on the processor
Computer program, which is characterized in that the processor is realized when executing the computer program as claim 1 to 6 is any
The step of item the method.
10. a kind of computer readable storage medium, the computer-readable recording medium storage has computer program, and feature exists
In when the computer program is executed by processor the step of any one of such as claim 1 to 6 of realization the method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910385803.6A CN110246472B (en) | 2019-05-09 | 2019-05-09 | Music style conversion method and device and terminal equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910385803.6A CN110246472B (en) | 2019-05-09 | 2019-05-09 | Music style conversion method and device and terminal equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110246472A true CN110246472A (en) | 2019-09-17 |
| CN110246472B CN110246472B (en) | 2024-05-24 |
Family
ID=67883970
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910385803.6A Active CN110246472B (en) | 2019-05-09 | 2019-05-09 | Music style conversion method and device and terminal equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110246472B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111326131A (en) * | 2020-03-03 | 2020-06-23 | 北京香侬慧语科技有限责任公司 | Song conversion method, device, equipment and medium |
| CN112216257A (en) * | 2020-09-29 | 2021-01-12 | 南方科技大学 | Music style migration method, model training method, device and storage medium |
| CN112820255A (en) * | 2020-12-30 | 2021-05-18 | 北京达佳互联信息技术有限公司 | Audio processing method and device |
| EP3826000A1 (en) * | 2019-11-21 | 2021-05-26 | Spotify AB | Automatic preparation of a new midi file |
| CN113539215A (en) * | 2020-12-29 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Music style conversion method, device, equipment and storage medium |
| CN115273866A (en) * | 2022-06-23 | 2022-11-01 | 天水师范学院 | Audio conversion method, device and storage medium |
| CN115297108A (en) * | 2022-08-11 | 2022-11-04 | 青岛美迪康数字工程有限公司 | Diagnosis and treatment quality control file transmission method and device based on piano syllables |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5889224A (en) * | 1996-08-06 | 1999-03-30 | Yamaha Corporation | Karaoke scoring apparatus analyzing singing voice relative to melody data |
| US20020134219A1 (en) * | 2001-03-23 | 2002-09-26 | Yamaha Corporation | Automatic music composing apparatus and automatic music composing program |
| JP2005025715A (en) * | 2002-11-25 | 2005-01-27 | Matsushita Electric Ind Co Ltd | Device and method for producing and reproducing short film |
| JP2011118218A (en) * | 2009-12-04 | 2011-06-16 | Ryukoku Univ | Automatic arrangement system and automatic arrangement method |
| CN105810209A (en) * | 2016-01-04 | 2016-07-27 | 邱子皓 | Data conversion method based on mapping relation |
| CN108231046A (en) * | 2017-12-28 | 2018-06-29 | 腾讯音乐娱乐科技（深圳）有限公司 | The recognition methods of song tonality and device |
-
2019
- 2019-05-09 CN CN201910385803.6A patent/CN110246472B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5889224A (en) * | 1996-08-06 | 1999-03-30 | Yamaha Corporation | Karaoke scoring apparatus analyzing singing voice relative to melody data |
| US20020134219A1 (en) * | 2001-03-23 | 2002-09-26 | Yamaha Corporation | Automatic music composing apparatus and automatic music composing program |
| JP2005025715A (en) * | 2002-11-25 | 2005-01-27 | Matsushita Electric Ind Co Ltd | Device and method for producing and reproducing short film |
| JP2011118218A (en) * | 2009-12-04 | 2011-06-16 | Ryukoku Univ | Automatic arrangement system and automatic arrangement method |
| CN105810209A (en) * | 2016-01-04 | 2016-07-27 | 邱子皓 | Data conversion method based on mapping relation |
| CN108231046A (en) * | 2017-12-28 | 2018-06-29 | 腾讯音乐娱乐科技（深圳）有限公司 | The recognition methods of song tonality and device |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11676565B2 (en) | 2019-11-21 | 2023-06-13 | Spotify Ab | Automatic preparation of a new MIDI file |
| EP3826000A1 (en) * | 2019-11-21 | 2021-05-26 | Spotify AB | Automatic preparation of a new midi file |
| EP3989216A1 (en) * | 2019-11-21 | 2022-04-27 | Spotify AB | Automatic preparation of a new midi file |
| CN111326131B (en) * | 2020-03-03 | 2023-06-02 | 北京香侬慧语科技有限责任公司 | Song conversion method, device, equipment and medium |
| CN111326131A (en) * | 2020-03-03 | 2020-06-23 | 北京香侬慧语科技有限责任公司 | Song conversion method, device, equipment and medium |
| CN112216257B (en) * | 2020-09-29 | 2023-08-15 | 南方科技大学 | Music style migration method, model training method, device and storage medium |
| CN112216257A (en) * | 2020-09-29 | 2021-01-12 | 南方科技大学 | Music style migration method, model training method, device and storage medium |
| CN113539215A (en) * | 2020-12-29 | 2021-10-22 | 腾讯科技（深圳）有限公司 | Music style conversion method, device, equipment and storage medium |
| CN113539215B (en) * | 2020-12-29 | 2024-01-12 | 腾讯科技（深圳）有限公司 | Music style conversion method, device, equipment and storage medium |
| CN112820255A (en) * | 2020-12-30 | 2021-05-18 | 北京达佳互联信息技术有限公司 | Audio processing method and device |
| CN115273866A (en) * | 2022-06-23 | 2022-11-01 | 天水师范学院 | Audio conversion method, device and storage medium |
| CN115273866B (en) * | 2022-06-23 | 2024-05-10 | 天水师范学院 | Audio conversion method, device and storage medium |
| CN115297108A (en) * | 2022-08-11 | 2022-11-04 | 青岛美迪康数字工程有限公司 | Diagnosis and treatment quality control file transmission method and device based on piano syllables |
| CN115297108B (en) * | 2022-08-11 | 2023-08-25 | 青岛美迪康数字工程有限公司 | Diagnosis and treatment quality control file transmission method and device based on piano syllables |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110246472B (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110246472A (en) | A kind of conversion method of music style, device and terminal device | |
| Yang et al. | MidiNet: A convolutional generative adversarial network for symbolic-domain music generation | |
| CN101950377A (en) | The new method of novel Markov sequence maker and generation Markov sequence | |
| KR20090051173A (en) | Method and device for the automatic or semi-automatic composition of a multimedia sequence | |
| Nakamura et al. | Statistical piano reduction controlling performance difficulty | |
| US20200228596A1 (en) | Streaming music categorization using rhythm, texture and pitch | |
| CN109326270A (en) | Generation method, terminal device and the medium of audio file | |
| JP2000221968A (en) | Automatic musical composition device and memory medium | |
| CN102541980A (en) | Information processing apparatus, information processing method, and program | |
| CN110867174A (en) | Automatic sound mixing device | |
| SE527425C2 (en) | Procedure and apparatus for musical depiction of an external process | |
| CN110134823B (en) | MIDI music genre classification method based on normalized note display Markov model | |
| US10431191B2 (en) | Method and apparatus for analyzing characteristics of music information | |
| CN112420002A (en) | Music generation method, device, electronic equipment and computer readable storage medium | |
| WO1999046758A1 (en) | Method for automatically controlling electronic musical devices by means of real-time construction and search of a multi-level data structure | |
| Hirata et al. | Interactive Music Summarization based on GTTM. | |
| CN110516103A (en) | Song rhythm generation method, equipment, storage medium and device based on classifier | |
| CN114461885A (en) | Song quality evaluation method, device and storage medium | |
| CN109448697A (en) | Poem melody generation method, electronic device and computer readable storage medium | |
| Dubnov et al. | Delegating creativity: Use of musical algorithms in machine listening and composition | |
| CN114267318A (en) | Method for generating Midi music file, storage medium and terminal | |
| CN113140202A (en) | Information processing method, information processing device, electronic equipment and storage medium | |
| JP2006201278A (en) | Method and apparatus for automatically analyzing metrical structure of piece of music, program, and recording medium on which program of method is recorded | |
| CN109903744B (en) | Melody generation method, melody generation device, computer-readable storage medium, and computer apparatus | |
| CN112989109A (en) | Music structure analysis method, electronic equipment and storage medium |
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 | ||
| GR01 | Patent grant |