CN104992712A - Music reorganization-based music score automatic formation method - Google Patents
Music reorganization-based music score automatic formation method Download PDFInfo
- Publication number
- CN104992712A CN104992712A CN201510389632.6A CN201510389632A CN104992712A CN 104992712 A CN104992712 A CN 104992712A CN 201510389632 A CN201510389632 A CN 201510389632A CN 104992712 A CN104992712 A CN 104992712A
- Authority
- CN
- China
- Prior art keywords
- pitch
- music
- note
- sounding
- confidence
- 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
Landscapes
- Auxiliary Devices For Music (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention discloses a music reorganization-based music score automatic formation method. The method includes the following steps that: (1) audios are recognized, the changes of the whole frequency spectrum of the audios are tracked, and sound emitting trends are checked in real time; (2) the frequency spectrum changes of each pitch are tracked, and pitches requiring sound emitting are checked in real time; (3) the frequency spectrum changes of pitches of which the sound emitting has been completed are further tracked, and whether judgment on sound emitting of the previous pitches is wrong is checked; and (4) the speed, tone and note type of a music score are estimated according to sound-emitting pitch data and sound-emitting time data obtained in the above steps, so that the music score can be composed. According to the music reorganization-based music score automatic formation method, an original music score can be estimated reversely according to pitch reorganization results, and thus, audio music can be automatically identified, and a music score can be automatically formed. The music reorganization-based music score automatic formation method has the advantages of simple calculation, robustness in sound emission number, compatibility with requirements of a variety of musical instruments as well as being efficient and reliable. The music reorganization-based music score automatic formation method can be applied to mobile phone software and embedded equipment, and can be also applied to occasions such as composition creation automatic music score formation and musical instrument playing exercise check.
Description
Technical field
The present invention relates to and can identify that music becomes the method for spectrum automatically, belong to the identification of music pitch, multitone identification, automatically form the technical fields such as the music score of Chinese operas.
Background technology
Pitch recognition technology tool has been widely used, and can be used for the aspects such as organ stop, melody identification and audio file conversion.In the organ stop of musical instrument, mainly can apply to the pitch recognition technology of single-tone, utilize the fundamental frequency of harmonic spike method sound recognition, check whether musical instrument pitch frequencies offsets to some extent, but the pitch identification that this technology realizes can only recognize single-tone, if several pitch that sounds is by None-identified simultaneously.And in the application of melody identification, pitch recognition technology can be utilized to identify roughly the melody that user hums, search in this, as basis of characterization and mate associated song.In digital audio file, generally be divided into waveform audio file (comprising mp3, wav etc.) and MIDI musical instrument digital interface file, wherein waveform audio file only records the waveform recording information of this audio frequency, MIDI file is then the music score of Chinese operas information of recording musical, at present, people also do not have effective method that waveform audio file is converted to MIDI file, and the professional person being familiar with music can only be relied on again to write out the original music score of Chinese operas by auditory experience.
The technology being applied to pitch identification at present mainly contains harmonic spike method, parallel processing method, wavelet analysis method etc.Wherein harmonic spike method performs an analysis for frequency domain harmonic, advantage is that method intuitively can realize, operand is little, but owing to depending on the maximum harmonic wave of energy as analyzing point, the situation of multitone identification cannot be analyzed, simultaneously because musical instrument pronounces the skew of frequent harmonic wave, often there is the inaccurate situation of fundamental frequency analyzed.Parallel processing method carries out audio analysis for time domain, carry out the principle of periodically regular superposition according to the harmonic wave of fundamental tone and fundamental tone on a timeline, estimate two peak-to-peak distances of ripple, calculate the audio frequency cycle thus, advantage is computing and realizes all fairly simple, and shortcoming is unstable result.Wavelet analysis rule utilizes wavelet transformation to make deep analysis frequency domain character, and extract fundamental tone, its advantage is that accuracy rate is higher, and shortcoming is that operand is too large.
And multitone estimation technique, always be the difficult point in music recognition, from the Stanford University scholar Moore of the seventies begins one's study, " sensory information of music signal extracts " research project of Osaka University eighties, Hawley and the Martin project of Massachusetts Institute of Technology (MIT), the Kashino project of Tokyo University, the Sterian project of University of Michigan, the Douglas Nunn projects of Da Lamo university etc. are all corresponding achieves research breakthrough, but there is not a computing simple all the time, efficiently credible, pronunciation number has robustness, the method of compatible various musical instrument can be applicable to the small-sized arithmetic facility software in non-laboratory, as smart mobile phone, Intelligent flat, insertion type equipment etc.
Summary of the invention
The object of the present invention is to provide and can identify that music becomes the method for spectrum automatically, the present invention has created one can according to pitch recognition result, the reverse technology estimating the original music score of Chinese operas, and final complete realization identifies that audio music forms the method for the music score of Chinese operas automatically automatically.This technology can be applicable to composition creation and automatically becomes the scenes such as spectrum, instrument playing exercise inspection.
To achieve these goals, the technical solution used in the present invention is as follows:
Can identify that music becomes the method for spectrum automatically, comprise the steps:
(1) environmental noise spectrum analysis is done, wherein decibel (dB) is got by energy value unit, environmental noise is carried out to the sampling of a period of time, record environmental noise within this period average frequency spectrum energy value distribution A and each frequency band energy at the standard deviation V of Annual distribution, the sounding energy threshold TTL of each frequency band can be drafted according to above two Data distribution8 in step afterwards.Principle is: higher at the noise energy mean value of certain frequency band, sounding energy threshold is higher; Noise energy standard deviation is higher, and sounding energy threshold is higher.Generally can draft sounding energy threshold as follows: TTL=A x P+V x Q; Wherein P, Q are the fixed values of getting by experience, environmentally can regulate, generally get P=3, Q=1.
(2) follow the trail of overall spectrum change, whether real-time inspection has pronunciation trend.Set effective articulation frequency range, the fundamental frequency frequency domain of standard piano pronunciation is about 27.5HZ to 4186HZ, considers that fundamental frequency offsets and reserves the domain space of 4 ~ 5 times of harmonics, and the effective articulation frequency range of general setting is 20HZ to 20000HZ.Calculate current spectral within the scope of this and exceed the area A rea of sounding energy threshold, if this area is greater than default area-limit Attl, then think that audio frequency now has pronunciation trend, otherwise think that present video is still quiet.
(3) follow the trail of the spectral change of each pitch, which is pitch sounding to real-time inspection.For the pitch of each potential sounding, analyze the peak value whether fundamental frequency of this pitch and harmonics exist interval energy, whether, and this peak value must be greater than sounding energy threshold is just included into calculating, exist and the size of peak value according to peak value, calculating each pitch may the degree of confidence L of sounding.Then whether satisfied two conditions of pitch that degree of confidence is maximum are checked: 1) now the confidence value L of this pitch becomes sharp increase state from steady or decline state suddenly, and namely satisfied (current confidence value L is greater than the certain multiple of the confidence value of former frame
), and meet (confidence value of former frame will within the scope of the certain proportion of degree of confidence average within a bit of time before, namely former frame degree of confidence in steadily or decline state); 2) whether the ratio that degree of confidence maximal value accounts for all pitch confidence value summations is greater than threshold values, namely satisfies condition.If meet above two conditions, then think this pitch sounding at this moment, eliminate the fundamental frequency of this pitch and the peak value of harmonics to the impact of other pitches simultaneously, calculate the confidence value of other pitches, to the judgement of above two conditions of pitch circulation of remaining degree of confidence maximal value, continue the pitch finding sounding, stop until above two conditions cannot be met.
(4) continue to follow the trail of the spectral change of sounding pitch, the sounding before inspection judges whether erroneous judgement.In instruments sound, after a general pitch sounding, all can there be continuity within a short period of time, and setting-up time length t is the time range checking erroneous judgement, if find that the during this period of time confidence value decay of sounding pitch is too fast, then thinks that this pitch sounding is for erroneous judgement.I.e. Rule of judgment, being wherein confidence value during this pitch sounding, is elapsed time after sounding, is a fixed value, can regulate the size of decline threshold values according to factors such as every frame sampling time interval, pitch, environment.If non real-time analysis, but for the analysis of misjudgement of complete audio file, after step can be inserted in and judge pitch sounding in step (3) at every turn.
(5) according to sounding pitch data, phonation time data that above step obtains, the speed of the music score of Chinese operas, mode and note type is estimated.
The principle of velocity estimation makes the actual duration of each note as far as possible near the note duration of estimation.Method is as follows:
1) pre-set velocity scope, the velocity range of general melody is per minute 30 ~ 240 four points bats; 2) for each velocity amplitude, according to the time interval of each pitch sounding, estimate the time long type of this note, during restriction, long type is whole note, minim, crotchet, quaver, semiquaver, the time span scope of long type during by rationally drafting every class, if there is duration to exceed whole note, fill the duration of unnecessary blank with whole tone rest, when can all notes all be concluded above accordingly in long type; 3) calculate the deviate that the actual duration of each note is grown on time with this speed subscript, being wherein the actual duration of note, is standard duration; 4) more all speed lower deviation value summations, the speed of getting under minimum deviation value is estimated speed.
The principle of mode estimation is, first make the few appearance as far as possible of increase and decrease sound, next makes the five notes of traditional Chinese music (do, re, mi, so, la) ratio conventional under this mode maximum, is finally as far as possible few rising-falling tone.Method is as follows:
1) for 12 large ditties (because each large tune can be equivalent to a ditty, therefore be directly fixedly judged as certain large tune), the increase and decrease sound number n, the five notes of traditional Chinese music number m that judge to occur under this mode, this mode lifting number number d (positive number represents sharp number, negative number representation flat number); 2) filter out the mode that increase and decrease sound number is minimum, meet if there is two or more mode simultaneously, then continue screening; 3) filter out the maximum mode of five notes of traditional Chinese music number further, meet if still there is two or more mode simultaneously, then continue screening; 4) filter out lifting number further minimum, still there are two the same modes of lifting number if final, then filter out the mode of rising tune.
The principle that note type is estimated records faithfully note duration and makes the music score of Chinese operas attractive in appearance, few note occurring leap trifle.Method is as follows:
1) when limiting, long type has whole note, minim is added some points, minim, crotchet are added some points, crotchet, quaver are added some points, quaver, semiquaver, long type corresponding true duration scope when defining each, when concluding all notes above in long type; 2) according to note order, the note of suitable quantity is concluded in a trifle.Exceed whole note if there is note duration, then allow this note duration become long type when arriving before little section end, remaining duration rest is filled; Cross over trifle if there is note, and within eight points of bats start in trifle of end point, then this note duration is changed at previous little section end; Last eight points that end up in trifle if there is note end point clap within, and next note duration exceedes or equals crotchet, then allow next note directly appear at the beginning of next trifle.
According to above step, finally can realize identifying pitch and the speed, mode, the note information that estimate the music score of Chinese operas, generate the music score of Chinese operas.
Compared with prior art, the present invention has following beneficial effect:
(1) the present invention uses pitch recognition technology, utilizes brand-new frequency spectrum analysis method, can meet the requirement of multitone identification, applies in cell phone software, insertion type equipment.
(2) the present invention created one can according to pitch recognition result, the reverse technology estimating the original music score of Chinese operas, final complete realization identifies that audio music forms the method for the music score of Chinese operas automatically automatically.This technology can be applicable to composition creation and automatically becomes the scenes such as spectrum, instrument playing exercise inspection.
(3) the present invention is directed to real-time audio stream and complete audio file all can be analyzed, computing and realize all fairly simple, and result is efficiently credible, compatible multiple musical instrument, there is outstanding substantive distinguishing features and significant progressive.
Embodiment
Below in conjunction with embodiment, the invention will be further described, and embodiments of the present invention include but not limited to the following example.
Embodiment
Can identify that music becomes the method for spectrum automatically, all can analyze for real-time audio stream and complete audio file, the present embodiment explains with real-time audio flow analysis, sampling rate is 44100HZ, be one group with 2048 sample points and carry out a sample analysis, be i.e. about 0.04644 second interval time (sample spaced by time=1 second ÷ sampling rate) of each sample analysis.
(1) before recognition, first can sample to environmental noise, the duration is 0.5 second, and namely about have 10 sample analysis data, concrete grammar is as follows:
Each sample analysis data be this sample time point region spectrum energy Distribution value (X-axis is frequency, Y-axis is energy value), and the peaceful mean square deviation of the average u (x) that can calculate 10 samples thus, wherein N=10, being i-th sample analysis at energy value corresponding to frequency x, is the average of energy value in 10 sampling analyses that frequency x is corresponding.The distribution of sounding energy threshold TTL can be calculated thus, wherein get P=3, Q=1.
(2) then start Real time identification music, whether real-time inspection has pronunciation trend, and concrete grammar is as follows:
In sample analysis each afterwards, will calculate frequency plane for its frequency spectrum and amass S, formula is, wherein, M represents the sample point number of each sample analysis, and namely M=2048, L are the frequency accuracies in sample analysis, frequency accuracy=sampling rate ÷ 2 ÷ sample point number, about L=10.77, the frequency spectrum area S real-time by comparative sample analysis and the frequency spectrum area of sounding energy threshold, if, then think now have pronunciation trend, Attl is adjustable empirical value.
(3) then check for the pitch value of each possibility sounding, attention might not check for all standard pronunciation high level, if known sounding musical instrument can not send some pitch value, then can not check this pitch value, concrete method is as follows:
Wherein, the computing formula of degree of confidence, wherein K represents maximum harmonics multiple, generally getting K=10, is the peak value of the interval energy existed near this harmonics, and the interval of general this harmonics of definition is, it is wherein fundamental frequency, p representative allows the number percent of harmonics skew fundamental frequency, and general harmonics multiple is larger, offsets more to the right.Then by (current confidence value L is greater than the certain multiple of the confidence value of former frame), (confidence value of former frame will within the scope of the certain proportion of degree of confidence average within a bit of time before, namely the degree of confidence of former frame is in steady or decline state), judge whether each potential pitch pronounces, if meet above condition, then think this pitch sounding at this moment.Wherein according to getting empirical value, according to potential pitch number, suppose that sounding musical instrument is 88 key pianos, potential pitch number is 88, then get, and circulation performs judgement, till judging all sounding pitches satisfied condition.
(4) if find that there is pitch sounding, 3 sample analysis points after sounding pitch can check whether erroneous judgement, namely judging the supervision time by accident continues about 0.14 second, Rule of judgment can be reduced to discrete under middle i=1,2,3; Get 0.5 respectively, 0.6,0.7.
(5) last, according to the sounding pitch data recognized and phonation time data, estimate the speed of the music score of Chinese operas, mode and note type, generate the music score of Chinese operas.The effective note type wherein estimated can increase and decrease according to actual needs.
The principle of velocity estimation is: make the actual duration of each note as far as possible near the note duration of estimation.Method is as follows:
1) pre-set velocity scope, the velocity amplitude scope of general melody is per minute 30 ~ 240 four points bats;
2) for each velocity amplitude, according to the time interval of each pitch sounding, estimate the time long type of this note, during restriction, long type is whole note, minim, crotchet, quaver, semiquaver, the time span scope of long type during by rationally drafting every class, if there is duration to exceed whole note, fill the duration of unnecessary blank with whole tone rest, when can all notes all be concluded above accordingly in long type;
3) calculate the deviate that the actual duration of each note is grown on time with this speed subscript, being wherein the actual duration of note, is standard duration;
4) more all speed lower deviation value summations, the speed of getting under minimum deviation value is estimated speed.
The principle of mode estimation is: first make the few appearance as far as possible of increase and decrease sound, next makes the five notes of traditional Chinese music (do, re, mi, so, la) ratio conventional under this mode maximum, is finally as far as possible few rising-falling tone.Method is as follows:
1) for 12 large ditties (because each large tune can be equivalent to a ditty, therefore be directly fixedly judged as certain large tune), the increase and decrease sound number n, the five notes of traditional Chinese music number m that judge to occur under this mode, this mode lifting number number d (positive number represents sharp number, negative number representation flat number);
2) filter out the mode that increase and decrease sound number is minimum, meet if there is two or more mode simultaneously, then continue screening;
3) filter out the maximum mode of five notes of traditional Chinese music number further, meet if still there is two or more mode simultaneously, then continue screening;
4) filter out lifting number further minimum, still there are two the same modes of lifting number if final, then filter out the mode of rising tune.
The principle that note type is estimated is: record faithfully note duration and make the music score of Chinese operas attractive in appearance, few note occurring leap trifle.Method is as follows:
1) when limiting, long type has whole note, minim is added some points, minim, crotchet are added some points, crotchet, quaver are added some points, quaver, semiquaver, long type corresponding true duration scope when defining each, when concluding all notes above in long type;
2) according to note order, the note of suitable quantity is concluded in a trifle.Exceed whole note if there is note duration, then allow this note duration become long type when arriving before little section end, remaining duration rest is filled; Cross over trifle if there is note, and within eight points of bats start in trifle of end point, then this note duration is changed at previous little section end; Last eight points that end up in trifle if there is note end point clap within, and next note duration exceedes or equals crotchet, then allow next note directly appear at the beginning of next trifle.
According to above-described embodiment, just the present invention can be realized well.What deserves to be explained is; under prerequisite based on said structure design, for solving same technical matters, even if some making on the invention are without substantial change or polishing; the essence of the technical scheme adopted is still the same with the present invention, therefore it also should in protection scope of the present invention.
Claims (7)
1. can identify that music becomes the method for spectrum automatically, it is characterized in that, comprise the steps:
(1) identify audio frequency, follow the trail of the change of overall spectrum, whether real-time inspection has pronunciation trend;
(2) follow the trail of the spectral change of each pitch, which is pitch sounding to real-time inspection;
(3) continue to follow the trail of the spectral change of sounding pitch, the pitch sounding before inspection judges whether it is erroneous judgement;
(4) according to sounding pitch data, phonation time data that above step obtains, estimate the speed of the music score of Chinese operas, mode and note type, generate the music score of Chinese operas.
2. according to claim 1 can identify music automatically become spectrum method, it is characterized in that, described step (1) is front, and also need to do environmental noise spectrum analysis, concrete grammar is:
(L1) decibel is got by energy value unit, environmental noise is carried out to the sampling of a period of time, and the average frequency spectrum energy value distribution A of record environmental noise within this period and each frequency band energy are at the standard deviation V of Annual distribution;
(L2) draft the sounding energy threshold TTL of each frequency band according to average frequency spectrum energy value distribution A and standard deviation V, TTL=A x P+V x Q, P, Q are fixed value.
3. according to claim 2 can identify music automatically become spectrum method, it is characterized in that, in described step (1), pronunciation trend inspection method be:
(11) setting effective articulation frequency range is 20HZ ~ 20000HZ;
(12) calculate current spectral within the scope of this and exceed the area A rea of sounding energy threshold;
(13) if this area A rea is greater than default area-limit Attl, then think that audio frequency now has pronunciation trend, otherwise, think that present video is still quiet.
4. according to claim 3 can identify music automatically become spectrum method, it is characterized in that, in described step (2), the inspection method of pitch sounding is:
(21) for the pitch of each potential sounding, analyze the peak value whether fundamental frequency of this pitch and harmonics exist interval energy, and this peak value must be greater than sounding energy threshold is just included into calculating;
(22) whether to exist according to peak value and the size of peak value, calculating each pitch may the degree of confidence L of sounding;
(23) check whether the maximum pitch of degree of confidence satisfies condition, if satisfy condition, then think this pitch sounding at this moment, eliminate the fundamental frequency of this pitch and the peak value of harmonics to the impact of other pitches simultaneously;
(24) calculate the degree of confidence L of other pitches, the judgement of above condition that the pitch that remaining degree of confidence is maximum is circulated, continue the pitch finding sounding, until stop when cannot satisfy condition.
5. according to claim 4ly can identify that music becomes the method for spectrum automatically, it is characterized in that, in described step (23), the condition that the maximum pitch of degree of confidence need meet simultaneously is:
The confidence value L of a, now this pitch becomes sharp increase state from steady or decline state suddenly, namely meets, and current confidence value L is greater than the certain multiple of the confidence value of former frame; And meet, the confidence value of former frame will for the previous period in degree of confidence average certain proportion within the scope of, namely the degree of confidence of former frame is in steady or decline state;
Whether the ratio that b, degree of confidence maximal value account for all pitch confidence value summations is greater than threshold values, namely meets.
6. according to claim 5 can identify music automatically become spectrum method, it is characterized in that, in described step (3), check whether that the method for erroneous judgement is:
(31) setting-up time length t is the time range checking erroneous judgement;
(32) if find that the confidence value decay in t during this period of time of sounding pitch is too fast, then think that this pitch sounding is for erroneous judgement, namely Rule of judgment is, wherein, being confidence value during this pitch sounding, is elapsed time after sounding, is a fixed value, for decline threshold values, L is the pad value of degree of confidence in time t.
7. according to claim 6ly can identify that music becomes the method for spectrum automatically, it is characterized in that, in described step (4), the method for speed of the estimation music score of Chinese operas is:
(411) pre-set velocity scope is per minute 30 ~ 240 four points bats;
(412) for each velocity amplitude, according to the time interval of each pitch sounding, estimate the time long type of this note, during restriction, long type is whole note, minim, crotchet, quaver, semiquaver, the time span scope of long type during by rationally drafting every class, if there is duration to exceed whole note, fill the duration of unnecessary blank with whole tone rest, when can all notes all be concluded above accordingly in long type;
(413) calculate the deviate that the actual duration of each note is grown on time with this speed subscript, being wherein the actual duration of note, is standard duration;
(414) more all speed lower deviation value summations, the speed of getting under minimum deviation value is estimated speed;
The method of estimation music score of Chinese operas mode is:
(421) for 12 large ditties, the increase and decrease sound number n, the five notes of traditional Chinese music number m that judge to occur under this mode, this mode lifting number number d, positive number represents sharp number, negative number representation flat number;
(422) filter out the mode that increase and decrease sound number is minimum, meet if there is two or more mode simultaneously, then continue screening;
(423) filter out the maximum mode of five notes of traditional Chinese music number further, meet if still there is two or more mode simultaneously, then continue screening;
(424) filter out lifting number further minimum, still there are two the same modes of lifting number if final, then filter out the mode of rising tune;
The method of estimation music score of Chinese operas note type is:
(431) when limiting, long type has whole note, minim is added some points, minim, crotchet are added some points, crotchet, quaver are added some points, quaver, semiquaver, long type corresponding true duration scope when defining each, when concluding all notes above in long type;
(432) according to note order, the note of suitable quantity is concluded in a trifle, exceedes whole note if there is note duration, then allow this note duration become long type when arriving before little section end, remaining duration rest is filled; Cross over trifle if there is note, and within eight points of bats start in trifle of end point, then this note duration is changed at previous little section end; Last eight points that end up in trifle if there is note end point clap within, and next note duration exceedes or equals crotchet, then allow next note directly appear at the beginning of next trifle.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510389632.6A CN104992712B (en) | 2015-07-06 | 2015-07-06 | It can identify music automatically at the method for spectrum |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510389632.6A CN104992712B (en) | 2015-07-06 | 2015-07-06 | It can identify music automatically at the method for spectrum |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104992712A true CN104992712A (en) | 2015-10-21 |
| CN104992712B CN104992712B (en) | 2019-02-12 |
Family
ID=54304515
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510389632.6A Expired - Fee Related CN104992712B (en) | 2015-07-06 | 2015-07-06 | It can identify music automatically at the method for spectrum |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104992712B (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105895079A (en) * | 2015-12-14 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | Voice data processing method and device |
| CN109979488A (en) * | 2019-03-14 | 2019-07-05 | 浙江大学 | Voice based on stress analysis turns music notation system |
| CN110933459A (en) * | 2019-11-18 | 2020-03-27 | 咪咕视讯科技有限公司 | Event video clipping method, device, server and readable storage medium |
| CN111343540A (en) * | 2020-03-05 | 2020-06-26 | 维沃移动通信有限公司 | Piano audio processing method and electronic equipment |
| CN111429779A (en) * | 2020-05-06 | 2020-07-17 | 福州天音树教育科技有限公司 | Paperless teaching and examination of music theory subject |
| CN112071287A (en) * | 2020-09-10 | 2020-12-11 | 北京有竹居网络技术有限公司 | Method, apparatus, electronic device and computer readable medium for generating song score |
| CN112634841A (en) * | 2020-12-02 | 2021-04-09 | 爱荔枝科技(北京)有限公司 | Guitar music automatic generation method based on voice recognition |
| CN113052138A (en) * | 2021-04-25 | 2021-06-29 | 广海艺术科创(深圳)有限公司 | Intelligent contrast correction method for dance and movement actions |
| CN113763913A (en) * | 2021-09-16 | 2021-12-07 | 腾讯音乐娱乐科技（深圳）有限公司 | Music score generation method, electronic device and readable storage medium |
| CN114078464A (en) * | 2022-01-19 | 2022-02-22 | 腾讯科技（深圳）有限公司 | Audio processing method, device and equipment |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102568456A (en) * | 2011-12-23 | 2012-07-11 | 深圳市万兴软件有限公司 | Notation recording method and a notation recording device based on humming input |
| CN103824565A (en) * | 2014-02-26 | 2014-05-28 | 曾新 | Humming music reading method and system based on music note and duration modeling |
| CN103854644A (en) * | 2012-12-05 | 2014-06-11 | 中国传媒大学 | Automatic duplicating method and device for single track polyphonic music signals |
| JP2014170251A (en) * | 2014-06-23 | 2014-09-18 | Yamaha Corp | Voice synthesis device, voice synthesis method and program |
-
2015
- 2015-07-06 CN CN201510389632.6A patent/CN104992712B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102568456A (en) * | 2011-12-23 | 2012-07-11 | 深圳市万兴软件有限公司 | Notation recording method and a notation recording device based on humming input |
| CN103854644A (en) * | 2012-12-05 | 2014-06-11 | 中国传媒大学 | Automatic duplicating method and device for single track polyphonic music signals |
| CN103824565A (en) * | 2014-02-26 | 2014-05-28 | 曾新 | Humming music reading method and system based on music note and duration modeling |
| JP2014170251A (en) * | 2014-06-23 | 2014-09-18 | Yamaha Corp | Voice synthesis device, voice synthesis method and program |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105895079A (en) * | 2015-12-14 | 2016-08-24 | 乐视网信息技术（北京）股份有限公司 | Voice data processing method and device |
| CN109979488A (en) * | 2019-03-14 | 2019-07-05 | 浙江大学 | Voice based on stress analysis turns music notation system |
| CN110933459A (en) * | 2019-11-18 | 2020-03-27 | 咪咕视讯科技有限公司 | Event video clipping method, device, server and readable storage medium |
| CN110933459B (en) * | 2019-11-18 | 2022-04-26 | 咪咕视讯科技有限公司 | Event video clipping method, device, server and readable storage medium |
| CN111343540B (en) * | 2020-03-05 | 2021-07-20 | 维沃移动通信有限公司 | Piano audio processing method and electronic equipment |
| CN111343540A (en) * | 2020-03-05 | 2020-06-26 | 维沃移动通信有限公司 | Piano audio processing method and electronic equipment |
| CN111429779A (en) * | 2020-05-06 | 2020-07-17 | 福州天音树教育科技有限公司 | Paperless teaching and examination of music theory subject |
| CN112071287A (en) * | 2020-09-10 | 2020-12-11 | 北京有竹居网络技术有限公司 | Method, apparatus, electronic device and computer readable medium for generating song score |
| CN112634841A (en) * | 2020-12-02 | 2021-04-09 | 爱荔枝科技(北京)有限公司 | Guitar music automatic generation method based on voice recognition |
| CN112634841B (en) * | 2020-12-02 | 2022-11-29 | 爱荔枝科技(北京)有限公司 | Guitar music automatic generation method based on voice recognition |
| CN113052138A (en) * | 2021-04-25 | 2021-06-29 | 广海艺术科创(深圳)有限公司 | Intelligent contrast correction method for dance and movement actions |
| CN113052138B (en) * | 2021-04-25 | 2024-03-15 | 广海艺术科创(深圳)有限公司 | Intelligent contrast correction method for dance and movement actions |
| CN113763913A (en) * | 2021-09-16 | 2021-12-07 | 腾讯音乐娱乐科技（深圳）有限公司 | Music score generation method, electronic device and readable storage medium |
| WO2023040332A1 (en) * | 2021-09-16 | 2023-03-23 | 腾讯音乐娱乐科技（深圳）有限公司 | Method for generating musical score, electronic device, and readable storage medium |
| CN114078464A (en) * | 2022-01-19 | 2022-02-22 | 腾讯科技（深圳）有限公司 | Audio processing method, device and equipment |
| CN114078464B (en) * | 2022-01-19 | 2022-03-22 | 腾讯科技（深圳）有限公司 | Audio processing method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104992712B (en) | 2019-02-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104992712A (en) | Music reorganization-based music score automatic formation method | |
| CN105405439B (en) | Speech playing method and device | |
| CN102664016B (en) | Singing evaluation method and system | |
| CN103823867B (en) | Humming type music retrieval method and system based on note modeling | |
| CN103714806B (en) | A kind of combination SVM and the chord recognition methods of in-dash computer P feature | |
| CN101373593B (en) | Speech analysis apparatus, speech analysis method and computer program | |
| US8193436B2 (en) | Segmenting a humming signal into musical notes | |
| CN104143324B (en) | A kind of musical tone recognition method | |
| Zlatintsi et al. | Multiscale fractal analysis of musical instrument signals with application to recognition | |
| CN109147765A (en) | Audio quality comprehensive evaluating method and system | |
| CN104217729A (en) | Audio processing method, audio processing device and training method | |
| CN110599987A (en) | Piano note recognition algorithm based on convolutional neural network | |
| CN105405448A (en) | Sound effect processing method and apparatus | |
| CN103824565A (en) | Humming music reading method and system based on music note and duration modeling | |
| CN104200818A (en) | Pitch detection method | |
| CN109979488A (en) | Voice based on stress analysis turns music notation system | |
| CN101290766A (en) | Syllable splitting method of Tibetan language of Anduo | |
| CN107978322A (en) | A kind of K songs marking algorithm | |
| CN108877835A (en) | Evaluate the method and system of voice signal | |
| CN105976803B (en) | A kind of note cutting method of combination music score | |
| CN105895079B (en) | Voice data processing method and device | |
| CN112634841B (en) | Guitar music automatic generation method based on voice recognition | |
| Stein | Automatic detection of multiple, cascaded audio effects in guitar recordings | |
| CN111681674B (en) | Musical instrument type identification method and system based on naive Bayesian model | |
| CN106649643B (en) | A kind of audio data processing method and its device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190212 Termination date: 20190706 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |