CN109493879A - Music rhythm rhythm analyzes extracting method and device - Google Patents

Music rhythm rhythm analyzes extracting method and device Download PDF

Info

Publication number
CN109493879A
CN109493879A CN201811578654.7A CN201811578654A CN109493879A CN 109493879 A CN109493879 A CN 109493879A CN 201811578654 A CN201811578654 A CN 201811578654A CN 109493879 A CN109493879 A CN 109493879A
Authority
CN
China
Prior art keywords
rhythm
phrase
music
target track
duration
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
Application number
CN201811578654.7A
Other languages
Chinese (zh)
Other versions
CN109493879B (en
Inventor
尹学渊
孟祥函
陈超
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Chengdu Potential Artificial Intelligence Technology Co ltd
Original Assignee
Chengdu Hi House Turning Technology Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Chengdu Hi House Turning Technology Co Ltd filed Critical Chengdu Hi House Turning Technology Co Ltd
Priority to CN201811578654.7A priority Critical patent/CN109493879B/en
Publication of CN109493879A publication Critical patent/CN109493879A/en
Application granted granted Critical
Publication of CN109493879B publication Critical patent/CN109493879B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10LSPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
    • G10L25/00Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/03Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10HELECTROPHONIC 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
    • G10H2210/00Aspects 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
    • G10H2210/031Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
    • G10H2210/051Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for extraction or detection of onsets of musical sounds or notes, i.e. note attack timings
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10HELECTROPHONIC 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
    • G10H2210/00Aspects 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
    • G10H2210/031Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
    • G10H2210/056Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for extraction or identification of individual instrumental parts, e.g. melody, chords, bass; Identification or separation of instrumental parts by their characteristic voices or timbres
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10HELECTROPHONIC 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
    • G10H2210/00Aspects 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
    • G10H2210/031Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
    • G10H2210/071Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for rhythm pattern analysis or rhythm style recognition
    • GPHYSICS
    • G10MUSICAL INSTRUMENTS; ACOUSTICS
    • G10HELECTROPHONIC 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
    • G10H2210/00Aspects 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
    • G10H2210/031Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal
    • G10H2210/076Musical analysis, i.e. isolation, extraction or identification of musical elements or musical parameters from a raw acoustic signal or from an encoded audio signal for extraction of timing, tempo; Beat detection

Abstract

The invention discloses a kind of music rhythm rhythm analysis extracting method and devices, are related to field of computer technology.This method comprises: pre-processing to MIDI music file, target track is obtained;All notes in target track are traversed, value and end duration at the beginning of each note are obtained;It identifies in target track and the sound root of string sound;Sound multiple in target track is processed into multiple single-tones;It is worth and terminates duration at the beginning of according to note, sound root, multiple single-tones and remaining note are spliced, obtain complete rhythm of melody, identifies the phrase in each period and each period in rhythm of melody;Similarity analysis is carried out to all phrases, the duration similarity of each phrase is obtained and marks corresponding label.Music rhythm rhythm analysis extracting method disclosed by the invention and device can realize extraction, analysis to music rhythm, can preferably excavate the information hidden in rhythm structure, preferably instruct the research and development of creation of computer music.

Description

Music rhythm rhythm analyzes extracting method and device
Technical field
The present invention relates to field of computer technology, analyze extracting method and dress more particularly, to a kind of music rhythm rhythm It sets.
Background technique
It improves with the development of science and technology, also gradually starts to apply using computer art music, create sound using computer It is happy, the mankind can be greatly reduced and carry out the workload of musical composition, and be expected to generate and shake off the novel music of conventional thought constraint, even if The music generated with computer can't be compared with the musician of the mankind, but machine works can provide candidate or primary for the mankind Works are more easier composer's creation, therefore have boundless application scenarios using computer art music.
In creation of computer music, analytic process, the extraction and analysis of music rhythm rhythm are essential one Process.Currently, existing technology is to be extracted by artificial or visualization tool to rhythm duration structure, it is difficult to apply to The scene largely calculated, and cannot be analysed scientifically with big data technology.
Summary of the invention
In view of this, it is an object of the invention to propose a kind of music rhythm rhythm analysis extracting method and device, with Improve the above problem.
To achieve the goals above, the present invention adopts the following technical scheme:
In a first aspect, the embodiment of the invention provides a kind of music rhythm rhythm to analyze extracting method, which comprises
MIDI music file is pre-processed, target track is obtained;
All notes in the target track are traversed, value and knot at the beginning of each note are obtained in the target track Beam duration;
It identifies in the target track and the sound root of string sound;
Multiple sound in the target track is processed into multiple single-tones;
It is worth and terminates duration at the beginning of according to note, the sound root, the multiple single-tone and remaining note is carried out Splicing, obtains complete rhythm of melody, remaining described note is that the polyphonic ring tone and the multiple sound are removed in the target track Except single-tone.
Music rhythm rhythm as described above analyzes extracting method, optionally, the method also includes:
Identify each period in the rhythm of melody;
Identify the phrase in each period;
Similarity analysis is carried out to all phrases, obtains the duration similarity of each phrase;
Corresponding label is marked to each phrase, wherein similarity is more than that label corresponding to the phrase of preset threshold is identical Or it is similar.
Music rhythm rhythm as described above analyzes extracting method, optionally, the method also includes:
Extract the duration structure of each period;
The phrase identified in each period, comprising:
According to the duration structure of each period, the phrase in each period is identified.
Music rhythm rhythm as described above analyzes extracting method, optionally, the method also includes:
Extract the duration structure of each phrase;
Described pair of all phrase carries out similarity analysis, comprising:
Similarity analysis is carried out to all phrases according to the duration structure of each phrase.
Music rhythm rhythm as described above analyzes extracting method, optionally, described to be located in advance to MIDI music file Reason, obtains target track, comprising:
It is extracted according to track of the predefined extracting parameter to MIDI file, obtains the target track, it is described to mention Taking parameter includes starting and end time.
Second aspect, the embodiment of the invention provides a kind of music rhythm rhythm to analyze extraction element, the music rhythm Rhythm analyzes extraction element
Preprocessing module obtains target track for pre-processing to MIDI music file;
It obtains module and obtains each note in the target track for traversing all notes in the target track At the beginning of be worth and terminate duration;
Identification module, for identification out in the target track and the sound root of string sound;
Processing module, for multiple sound in the target track to be processed into multiple single-tones;
Splicing module, for being worth and terminating duration at the beginning of according to note, to the sound root, the multiple single-tone and Remaining note is spliced, and complete rhythm of melody is obtained, remaining described note is that the polyphonic ring tone is removed in the target track With the single-tone except the multiple sound.
Music rhythm rhythm as described above analyzes extraction element, and optionally, dress is extracted in the music rhythm rhythm analysis Setting further includes similarity analysis module and mark module, and the identification module is also used to identify each of described rhythm of melody Period;And
Identify the phrase in each period;
The similarity analysis module is used to carry out similarity analysis to all phrases, obtains the duration phase of each phrase Like degree;
The mark module is used to mark corresponding label to each phrase, and wherein similarity is more than the phrase of preset threshold Corresponding label is same or similar.
Music rhythm rhythm as described above analyzes extraction element, and optionally, dress is extracted in the music rhythm rhythm analysis Setting further includes extraction module, and the extraction module is used to extract the duration structure of each period;
The identification module is used for the duration structure according to each period, identifies the phrase in each period.
Music rhythm rhythm as described above analyzes extraction element, and optionally, the extraction module is also used to extract often The duration structure of a phrase;
The similarity analysis module is used to carry out similitude point to all phrases according to the duration structure of each phrase Analysis.
Music rhythm rhythm as described above analyzes extraction element, and optionally, the preprocessing module is used for according to predetermined The extracting parameter of justice extracts the track of MIDI file, obtains the target track, and the extracting parameter includes when starting Between and the end time.
Compared with prior art, the beneficial effects of the present invention are:
Music rhythm rhythm provided by the invention analysis extracting method and device can realize extraction to music rhythm, point Analysis can preferably excavate the information hidden in rhythm structure, the research and development for preferably instructing Computer Music to create.It is existing Technology can not segment period and phrase in rhythm, and value is at the end of at the beginning of note can not be accurately navigated to by program Value, while the duration structure storage that also can not accurately analyze the analysis of duration structure rhythm based on this, characterize rhythm, The operation such as visable representation, this patent are conducive to make the above problem very good solution and solve the problems, such as some of.
Detailed description of the invention
Fig. 1 is the block diagram for the terminal device that present pre-ferred embodiments provide.
Fig. 2 is the flow chart that the music rhythm rhythm that present pre-ferred embodiments provide analyzes extracting method.
Fig. 3 is the functional block diagram that the music rhythm rhythm that present pre-ferred embodiments provide analyzes extraction element.
Description of symbols: 100- terminal device;110- music rhythm rhythm analyzes extraction element;111- pre-processes mould Block;112- obtains module;113- identification module;114- processing module;115- splicing module;116- similarity analysis module; 117- mark module;118- extraction module;120- memory;130- storage control;140- processor;150- Peripheral Interface; 160- input-output unit;170- display unit.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
Term " first ", " second ", " third " etc. are only used for distinguishing description, are not understood to indicate or imply relatively heavy The property wanted.
Music rhythm rhythm analysis extracting method provided in an embodiment of the present invention and device can be applied to end as shown in Figure 1 End equipment 100, in the embodiment of the present invention, the terminal device 100 can be PC (personal computer, PC), Tablet computer, smart phone, personal digital assistant (personal d igital assistant, PDA) etc..It should be understood that In other some embodiments, the terminal device 100 is also possible to network server, database server.
Referring to Fig. 1, the terminal device 100 includes to analyze extraction element 110, memory including music rhythm rhythm 120, storage control 130, processor 140, Peripheral Interface 150, input-output unit 160, display unit 170.
The memory 120, processor 140, Peripheral Interface 150, input-output unit 160, is shown storage control 130 Show that each element of unit 170 is directly or indirectly electrically connected between each other, to realize the transmission or interaction of data.For example, these Element can be realized by one or more communication bus or signal wire be electrically connected between each other.The music rhythm rhythm analysis Extraction element 110 include at least one can be stored in the form of software or firmware (firmware) in the memory 120 or The software function module being solidificated in the operating system (operating system, OS) of the electronic equipment 100.The processing Device 140 is for executing the executable module stored in memory 120, such as music rhythm rhythm analysis extraction element 110 Including software function module or computer program.
Wherein, memory 120 may be, but not limited to, random access memory (Random Access Memory, RAM), read-only memory (Read Only Memory, ROM), programmable read only memory (Programmable Read-Only Memory, PROM), erasable read-only memory (Erasable Programmable Read-Only Memory, EPROM), Electricallyerasable ROM (EEROM) (Electric Erasable Programmable Read-Only Memory, EEPROM) etc.. Wherein, memory 120 is for storing program, and the processor 140 executes described program after receiving and executing instruction, aforementioned Method performed by the terminal device 100 that the stream process that any embodiment of the embodiment of the present invention discloses defines can be applied to handle In device 140, or realized by processor 140.
Processor 140 may be a kind of IC chip, the processing capacity with signal.Above-mentioned processor 140 can To be general processor, including central processing unit (Central Processing Unit, abbreviation CPU), network processing unit (Network Processor, abbreviation NP) etc., can also be digital signal processor (DSP), specific integrated circuit (ASIC), Ready-made programmable gate array (FPGA) either other programmable logic device, discrete gate or transistor logic, discrete hard Part component.It may be implemented or execute disclosed each method, step and the logic diagram in the embodiment of the present invention.General processor It can be microprocessor or the processor be also possible to any conventional processor etc..
Various input/output devices are couple processor 140 and memory 120 by the Peripheral Interface 150.Some In embodiment, Peripheral Interface 150, processor 140 and storage control 130 can be realized in one single chip.Other one In a little examples, they can be realized by independent chip respectively.
Input-output unit 160 is used to be supplied to the interaction that user input data realizes user and the terminal device 100. The input-output unit 160 may be, but not limited to, mouse and keyboard etc..
Display unit 170 provides an interactive interface (such as user's operation circle between the terminal device 100 and user Face) or for display image data give user reference.In the present embodiment, the display unit 170 can be liquid crystal display Or touch control display.It can be the capacitance type touch control screen or resistance of support single-point and multi-point touch operation if touch control display Formula touch screen etc..Single-point and multi-point touch operation is supported to refer to that touch control display can sense on the touch control display one Or at multiple positions simultaneously generate touch control operation, and the touch control operation that this is sensed transfer to processor 140 carry out calculate and Processing.
Referring to Fig. 2, being that the music applied to terminal device 100 shown in FIG. 1 that present pre-ferred embodiments provide is revolved Restrain the flow chart of rhythm analysis extracting method.Detailed process shown in Fig. 2 will be described in detail below.
Step S101 pre-processes MIDI music file, obtains target track.
In the embodiment of the present invention, it is previously stored in the terminal device 100 for the analysis extraction of music rhythm rhythm MIDI music file, when carrying out the analysis extraction of music rhythm rhythm, terminal device 100 is to pre-stored MIDI music file Extract, extract the track in MIDI music file, obtain one or more target tracks, describe for convenience it is subsequent with One track is illustrated.
When extracting to MIDI music file, terminal device 100 can also define MIDI according to the defining operation of user The extracting parameter of music file, the extracting parameter include starting and end time, are mentioned to MIDI music file Terminal device 100 can extract one section of track from MIDI music file according to the extracting parameter when taking, and obtain target track.
Further, it is pre-processed to MIDI music file, after obtaining target track, terminal device 100 can also root Change according to bat number (BPM, the Beat Per Minute) evidence and beat of target track, track rhythm is calculated using relative time At the beginning of be worth.
Step S102 traverses all notes in target track, obtain in target track at the beginning of each note value with Terminate duration.
MIDI music file is pre-processed after obtaining target track, the terminal device 100 traverses in target track All notes, obtain in target track value at the beginning of each note and terminate duration, value is to refer to sound at the beginning of note Symbol in track at the beginning of, the ends duration of note be finger note the end time in track.
It can be a bat with 4 dieresis, if note is opened using 64 dieresis as unit duration that duration, which is calculated, in the present embodiment Time beginning or end time are note_time, and corresponding duration is note_time_value, the period where note First trifle at the beginning of be basic_start_time, rate locating for note is bpm, obtain following calculating process:
The duration unit_second (s) of 64 dieresis:
Unit_second=60/ (bpm*16).
The opposite beginning of note or end time calculate:
Note_relative_time=note_time-basic_start_time.
Note duration calculates:
Note_time_value=note_relative_time/unit_second.
In view of beat and rate can change, if the last one duration before variation is last_note_time_ Value, and recalculate basic_start_time, unit_secomd, note_relative_time etc., calculating becomes Duration after change:
Note_time_value=note_relative_time/unit_second+last_note _ time_value.
Step S103, is identified in target track and the sound root of string sound.
It include polyphonic ring tone and multiple sound in general one section of track, multiple sound refers to the sound in the multiple overlappings of same amount of time Symbol, therefore after obtaining target track, the terminal device 100 is according to the predefined music theory (music theory and practical pleasure of this definition Reason is consistent) identify that (chord must be established on some sound, this sound is exactly root with the sound root of string sound in target track Sound, that is, root.For example it is exactly domi sol that common chords are established on do, the sound root of the common chords is exactly do.It is built on re Vertical seventh chord is exactly re fa la do, and the sound root of the seventh chord is exactly re).
Sound multiple in target track is processed into multiple single-tones by step S104.
At the same time, the note being overlapped in multiple sound is split processing by the terminal device 100, will be more in multiple sound The note of a overlapping is processed into multiple single-tones, and the single-tone that target track Central Plains has then retains.
Step S105, according to note at the beginning of be worth and terminate duration, to sound root, multiple single-tones and remaining note carry out Splicing, obtains complete rhythm of melody.
The terminal device 100 has traversed all notes in target track, and obtains each note in target track Start duration and terminates duration.Multiple sound is processed into multiple in identifying target track and in the sound root of string sound, target track Single-tone and remaining note are spliced, and complete rhythm of melody is obtained.Remaining described note refers in target track except described Single-tone except polyphonic ring tone and the multiple sound.
Wherein, when being spliced, the terminal device 100 according to each note at the beginning of be worth and terminate duration, press Sound root, multiple single-tones and remaining note are spliced according to sequencing, it is so i.e. feasible completely to meet rhythm at one section Variation, and have the melody of ornamental value.
Step S106 identifies each period in rhythm of melody.
Further, after splicing obtains complete rhythm of melody, the terminal device 100 can also be according to the rhythm of melody Duration structure recognition go out each period in rhythm of melody.
Step S107 identifies the phrase in each period.
Then, the terminal device 100 extracts the duration structure of each period, is identified often according to the duration result of extraction Phrase in a period.
The duration structure of note in the embodiment of the present invention are as follows:
Start duration: the duration point of note relative start time.
Terminate duration: the duration point of note relative ending time.
Since the note in track is continuous object, so the duration structure of track is note duration structure sequence, indicate It is as follows:
[(starting duration 1, terminate duration 1), (starting duration 2, terminate duration 2) ...]
Label information, label information can also be added for track duration structure simultaneously can include:
The similar structure of phrase: this patent illustrates process with this label.
Track musical instrument: the musical instrument that the track uses is numbered for MIDI musical instrument.
Average pitch: all note pitch average values.
Average dynamics: all note velocity average values.
Trifle number: the trifle quantity for including.
Mood classification: mood classification can do mood classification to MIDI file by decision Tree algorithms.
Rate: the BPM of MIDI.
Maximum pitch: the pitch maximum value occurred in note.
Minimum pitch: the pitch minimum value occurred in note.
It whether is theme: theme for identification.
Whether it is musical instrument solo: whether is for identification musical instrument solo.
Further, the duration structure and its information labels obtained can be easy to be structured into and can deposit for SQL database The structure of storage, and it is deposited into database.
Step S108 carries out similarity analysis to all phrases, obtains the duration similarity of each phrase.
After identifying the phrase in each period, the terminal device 100 extracts the duration structure of each phrase again, And similarity analysis is carried out to all phrases according to the duration structure of each phrase, the duration structure of two phrases is closer to then Illustrate that the similarity of two phrases is higher, each phrase in rhythm of melody can be analyzed by the duration structural analysis to phrase Similarity degree.
Step S109 marks corresponding label to each phrase.
The higher phrase of similarity, rhythm of melody is also more close, carries out greatly to further realize to music rhythm rhythm Data analysis, the terminal device 100 is in analyzing rhythm of melody after the duration similarity of each phrase, also to each phrase It marks corresponding label and stores, wherein similarity is more than that label corresponding to the phrase of preset threshold is same or similar.In this way, Corresponding same or similar label can be used to define the high phrase of same class similarity, to create in rear Computer Music Make, in analytic process, can preferably excavate the information hidden in rhythm structure, provide a large amount of number for creation of computer music According to support, the research and development of Computer Music wound is preferably instructed.
Referring to Fig. 3, being the function mould for the music rhythm rhythm analysis extraction element 110 that present pre-ferred embodiments provide Block schematic diagram, the music rhythm rhythm analysis extraction element 110 include preprocessing module 111, obtain module 112, identification mould Block 113, processing module 114, splicing module 115, similarity analysis module 116, mark module 117 and extraction module 118.
The preprocessing module 111 obtains target track for pre-processing to MIDI music file.
It should be understood that the preprocessing module 111 can be used for executing above-mentioned step S101.
The module 112 that obtains is used to traverse all notes in the target track, obtains every in the target track It is worth and terminates duration at the beginning of a note.
It should be understood that the acquisition module 112 can be used for executing above-mentioned step S102.
The identification module 113 goes out in the target track for identification and the sound root of string sound.
It should be understood that the identification module 113 can be used for executing above-mentioned step S103.
The processing module 114 is used to multiple sound in the target track being processed into multiple single-tones.
It should be understood that the processing module 114 can be used for executing above-mentioned step S104.
The splicing module 115 is used to be worth at the beginning of according to note and terminate duration, to the sound root, the multiple list Sound and remaining note are spliced, and complete rhythm of melody is obtained.
It should be understood that the splicing module 115 can be used for executing above-mentioned step S105.
The extraction module 118 is for extracting the duration structure of each period and the duration structure of each phrase.
The identification module 113 is also used to identify each period in the rhythm of melody, and identifies each pleasure Phrase in section.
It should be understood that the identification module 113 can be also used for executing above-mentioned step S106 and step S107.
The similarity analysis module 116 is used to carry out similarity analysis to all phrase, obtain each phrase when It is worth similarity.
It should be understood that the similarity analysis module 116 can be used for executing above-mentioned step S108.
The mark module 117 is used to mark corresponding label to each phrase.
It should be understood that the mark module 117 can be used for executing above-mentioned step S109.
In conclusion music rhythm rhythm provided by the invention analysis extracting method and device can traverse it is pretreated All notes in target track obtain value and end duration at the beginning of each note in target track, and identify target The sound root of polyphonic ring tone and sound multiple in target track is processed into multiple single-tones in track, then according to note at the beginning of be worth With end duration, sound root, multiple single-tones and remaining note are spliced, complete rhythm of melody is obtained.So, it can be achieved that Extraction, analysis to music rhythm, can preferably excavate the information hidden in rhythm structure, preferably instruct Computer Music The research and development of wound.Meanwhile also may recognize that the phrase in each period and each period in rule rhythm, and Similarity analysis is carried out to all phrases, it is happy more than preset threshold to similarity after obtaining the duration similarity of each phrase Sentence marks the same or similar label.In this way, corresponding same or similar label can be used to define same class similarity height Phrase, so as in rear creation of computer music, analytic process, be further able to preferably excavate rhythm structure in hide Information provides a large amount of data supporting for creation of computer music, the research and development for preferably instructing Computer Music to create.
In several embodiments provided herein, it should be understood that disclosed device and method can also pass through Other modes are realized.The apparatus embodiments described above are merely exemplary, for example, flow chart and block diagram in attached drawing Show the device of multiple embodiments according to the present invention, the architectural framework in the cards of method and computer program product, Function and operation.In this regard, each box in flowchart or block diagram can represent the one of a module, section or code Part, a part of the module, section or code, which includes that one or more is for implementing the specified logical function, to be held Row instruction.It should also be noted that function marked in the box can also be to be different from some implementations as replacement The sequence marked in attached drawing occurs.For example, two continuous boxes can actually be basically executed in parallel, they are sometimes It can execute in the opposite order, this depends on the function involved.It is also noted that every in block diagram and or flow chart The combination of box in a box and block diagram and or flow chart can use the dedicated base for executing defined function or movement It realizes, or can realize using a combination of dedicated hardware and computer instructions in the system of hardware.
In addition, each functional module in each embodiment of the present invention can integrate one independent portion of formation together Point, it is also possible to modules individualism, an independent part can also be integrated to form with two or more modules.
It, can be with if the function is realized and when sold or used as an independent product in the form of software function module It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention. And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.It needs Illustrate, herein, relational terms such as first and second and the like be used merely to by an entity or operation with Another entity or operation distinguish, and without necessarily requiring or implying between these entities or operation, there are any this realities The relationship or sequence on border.Moreover, the terms "include", "comprise" or its any other variant are intended to the packet of nonexcludability Contain, so that the process, method, article or equipment for including a series of elements not only includes those elements, but also including Other elements that are not explicitly listed, or further include for elements inherent to such a process, method, article, or device. In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including the element Process, method, article or equipment in there is also other identical elements.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, made any to repair Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.It should also be noted that similar label and letter exist Similar terms are indicated in following attached drawing, therefore, once being defined in a certain Xiang Yi attached drawing, are then not required in subsequent attached drawing It is further defined and explained.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.

Claims (10)

1. a kind of music rhythm rhythm analyzes extracting method, which is characterized in that the described method includes:
MIDI music file is pre-processed, target track is obtained;
Traverse all notes in the target track, obtain in the target track at the beginning of each note value and at the end of Value;
It identifies in the target track and the sound root of string sound;
Multiple sound in the target track is processed into multiple single-tones;
It is worth and terminates duration at the beginning of according to note, the sound root, the multiple single-tone and remaining note is spliced, Obtain complete rhythm of melody, remaining described note be in the target track in addition to the polyphonic ring tone and the multiple sound Single-tone.
2. music rhythm rhythm according to claim 1 analyzes extracting method, which is characterized in that the method also includes:
Identify each period in the rhythm of melody;
Identify the phrase in each period;
Similarity analysis is carried out to all phrases, obtains the duration similarity of each phrase;
Corresponding label is marked to each phrase, wherein similarity is more than that label corresponding to the phrase of preset threshold is identical or phase Seemingly.
3. music rhythm rhythm according to claim 2 analyzes extracting method, which is characterized in that the method also includes:
Extract the duration structure of each period;
The phrase identified in each period, comprising:
According to the duration structure of each period, the phrase in each period is identified.
4. music rhythm rhythm according to claim 3 analyzes extracting method, which is characterized in that the method also includes:
Extract the duration structure of each phrase;
Described pair of all phrase carries out similarity analysis, comprising:
Similarity analysis is carried out to all phrases according to the duration structure of each phrase.
5. music rhythm rhythm according to claim 1 analyzes extracting method, which is characterized in that described to MIDI music text Part is pre-processed, and target track is obtained, comprising:
It is extracted according to track of the predefined extracting parameter to MIDI file, obtains the target track, the extraction ginseng Number is including starting and end time etc..
6. a kind of music rhythm rhythm analyzes extraction element, which is characterized in that the music rhythm rhythm analyzes extraction element packet It includes:
Preprocessing module obtains target track for pre-processing to MIDI music file;
Module is obtained, for traversing all notes in the target track, obtains opening for each note in the target track Beginning duration and end duration;
Identification module, for identification out in the target track and the sound root of string sound;
Processing module, for multiple sound in the target track to be processed into multiple single-tones;
Splicing module, for being worth and terminating duration at the beginning of according to note, to the sound root, the multiple single-tone and remaining Note is spliced, and obtains complete rhythm of melody, remaining described note is removes the polyphonic ring tone and institute in the target track State the single-tone except multiple sound.
7. music rhythm rhythm according to claim 6 analyzes extraction element, which is characterized in that the music rhythm rhythm Analyzing extraction element further includes similarity analysis module and mark module, and the identification module is also used to identify the melody section Each period in playing;And
Identify the phrase in each period;
The similarity analysis module is used to carry out similarity analysis to all phrases, and the duration for obtaining each phrase is similar Degree;
The mark module is used to mark corresponding label to each phrase, and wherein similarity is more than that the phrase institute of preset threshold is right The label answered is same or similar.
8. music rhythm rhythm according to claim 7 analyzes extraction element, which is characterized in that the music rhythm rhythm Analyzing extraction element further includes extraction module, and the extraction module is used to extract the duration structure of each period;
The identification module is used for the duration structure according to each period, identifies the phrase in each period.
9. music rhythm rhythm according to claim 8 analyzes extraction element, which is characterized in that the extraction module is also used In the duration structure for extracting each phrase;
The similarity analysis module is used to carry out similarity analysis to all phrases according to the duration structure of each phrase.
10. music rhythm rhythm according to claim 6 analyzes extraction element, which is characterized in that the preprocessing module For extracting according to track of the predefined extracting parameter to MIDI file, the target track, the extraction ginseng are obtained Number is including starting and end time etc..
CN201811578654.7A 2018-12-24 2018-12-24 Music rhythm analysis and extraction method and device Active CN109493879B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811578654.7A CN109493879B (en) 2018-12-24 2018-12-24 Music rhythm analysis and extraction method and device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811578654.7A CN109493879B (en) 2018-12-24 2018-12-24 Music rhythm analysis and extraction method and device

Publications (2)

Publication Number Publication Date
CN109493879A true CN109493879A (en) 2019-03-19
CN109493879B CN109493879B (en) 2021-12-17

Family

ID=65711519

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811578654.7A Active CN109493879B (en) 2018-12-24 2018-12-24 Music rhythm analysis and extraction method and device

Country Status (1)

Country Link
CN (1) CN109493879B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110164470A (en) * 2019-06-12 2019-08-23 成都嗨翻屋科技有限公司 Voice separation method, device, user terminal and storage medium
CN110517655A (en) * 2019-08-28 2019-11-29 广州艾颂智能科技有限公司 A kind of melody generation method and system
CN111696500A (en) * 2020-06-17 2020-09-22 不亦乐乎科技(杭州)有限责任公司 Method and device for identifying MIDI sequence chord
CN112331170A (en) * 2020-10-28 2021-02-05 平安科技(深圳)有限公司 Method, device and equipment for analyzing similarity of Buddha music melody and storage medium
CN112691371A (en) * 2020-12-28 2021-04-23 完美世界(重庆)互动科技有限公司 Game audio output method and device, storage medium and electronic device
CN113192471A (en) * 2021-04-16 2021-07-30 南京航空航天大学 Music main melody track identification method based on neural network

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1737798A (en) * 2005-09-08 2006-02-22 上海交通大学 Music rhythm sectionalized automatic marking method based on eigen-note
CN105118490A (en) * 2015-07-20 2015-12-02 科大讯飞股份有限公司 Polyphonic musical instrument note positioning method and polyphonic musical instrument note positioning device
CN105205047A (en) * 2015-09-30 2015-12-30 北京金山安全软件有限公司 Playing method, converting method and device of musical instrument music score file and electronic equipment
US20160189698A1 (en) * 2013-03-15 2016-06-30 Exomens Ltd. System and method for analysis and creation of music
CN106205571A (en) * 2016-06-24 2016-12-07 腾讯科技(深圳)有限公司 A kind for the treatment of method and apparatus of singing voice
CN109068439A (en) * 2018-07-30 2018-12-21 上海应用技术大学 A kind of light coloring control method and its control device based on MIDI theme

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1737798A (en) * 2005-09-08 2006-02-22 上海交通大学 Music rhythm sectionalized automatic marking method based on eigen-note
US20160189698A1 (en) * 2013-03-15 2016-06-30 Exomens Ltd. System and method for analysis and creation of music
CN105118490A (en) * 2015-07-20 2015-12-02 科大讯飞股份有限公司 Polyphonic musical instrument note positioning method and polyphonic musical instrument note positioning device
CN105205047A (en) * 2015-09-30 2015-12-30 北京金山安全软件有限公司 Playing method, converting method and device of musical instrument music score file and electronic equipment
CN106205571A (en) * 2016-06-24 2016-12-07 腾讯科技(深圳)有限公司 A kind for the treatment of method and apparatus of singing voice
CN109068439A (en) * 2018-07-30 2018-12-21 上海应用技术大学 A kind of light coloring control method and its control device based on MIDI theme

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110164470A (en) * 2019-06-12 2019-08-23 成都嗨翻屋科技有限公司 Voice separation method, device, user terminal and storage medium
CN110517655A (en) * 2019-08-28 2019-11-29 广州艾颂智能科技有限公司 A kind of melody generation method and system
CN110517655B (en) * 2019-08-28 2023-03-14 广州艾颂智能科技有限公司 Melody generation method and system
CN111696500A (en) * 2020-06-17 2020-09-22 不亦乐乎科技(杭州)有限责任公司 Method and device for identifying MIDI sequence chord
CN111696500B (en) * 2020-06-17 2023-06-23 不亦乐乎科技(杭州)有限责任公司 MIDI sequence chord identification method and device
CN112331170A (en) * 2020-10-28 2021-02-05 平安科技(深圳)有限公司 Method, device and equipment for analyzing similarity of Buddha music melody and storage medium
CN112331170B (en) * 2020-10-28 2023-09-15 平安科技(深圳)有限公司 Method, device, equipment and storage medium for analyzing Buddha music melody similarity
CN112691371A (en) * 2020-12-28 2021-04-23 完美世界(重庆)互动科技有限公司 Game audio output method and device, storage medium and electronic device
CN113192471A (en) * 2021-04-16 2021-07-30 南京航空航天大学 Music main melody track identification method based on neural network
CN113192471B (en) * 2021-04-16 2024-01-02 南京航空航天大学 Musical main melody track recognition method based on neural network

Also Published As

Publication number Publication date
CN109493879B (en) 2021-12-17

Similar Documents

Publication Publication Date Title
CN109493879A (en) Music rhythm rhythm analyzes extracting method and device
Barbancho et al. Automatic transcription of guitar chords and fingering from audio
US8115089B2 (en) Apparatus and method for creating singing synthesizing database, and pitch curve generation apparatus and method
CN109166564A (en) For the method, apparatus and computer readable storage medium of lyrics text generation melody
CN109920449B (en) Beat analysis method, audio processing method, device, equipment and medium
CN104992712B (en) It can identify music automatically at the method for spectrum
CN109671416A (en) Music rhythm generation method, device and user terminal based on enhancing study
CN111081272A (en) Song climax fragment identification method and device
CN105389356B (en) A kind of musical database searching system based on feature extraction
CN108257588B (en) Music composing method and device
JPH09293083A (en) Music retrieval device and method
EP3726521A1 (en) Information processing method, information processing device, and information processing program
US20210241731A1 (en) Systems, devices, and methods for assigning mood labels to musical compositions
Kroher et al. Computational ethnomusicology: a study of flamenco and Arab-Andalusian vocal music
Yang Computational modelling and analysis of vibrato and portamento in expressive music performance
CN113421589A (en) Singer identification method, singer identification device, singer identification equipment and storage medium
CN108257591A (en) A kind of recognition methods of music and system
Hockman et al. Computational strategies for breakbeat classification and resequencing in hardcore, jungle and drum and bass
WO2022143679A1 (en) Sheet music analysis and marking method and apparatus, and electronic device
CN114461885A (en) Song quality evaluation method, device and storage medium
He A Music Genre Classification Method Based on Deep Learning
CN114238684A (en) Resource searching method and electronic equipment
Navarro-Cáceres et al. A user controlled system for the generation of melodies applying case based reasoning
Lai Automatic music classification model based on instantaneous frequency and CNNs in high noise environment
Kolhoff et al. Content-based icons for music files

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
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20230621

Address after: Room 1210, 12 / F, unit 1, building 1, No. 722, middle section of Yizhou Avenue, high tech Zone, Chengdu, Sichuan 610000

Patentee after: Chengdu potential Artificial Intelligence Technology Co.,Ltd.

Address before: 610000 Huayang Avenue Section 117 and 119, Huayang Street, Tianfu New District, Chengdu City, Sichuan Province

Patentee before: CHENGDU HIFIVE TECHNOLOGY Co.,Ltd.

TR01 Transfer of patent right