CN107103917A - Music rhythm detection method and its system - Google Patents
Music rhythm detection method and its system Download PDFInfo
- Publication number
- CN107103917A CN107103917A CN201710159699.XA CN201710159699A CN107103917A CN 107103917 A CN107103917 A CN 107103917A CN 201710159699 A CN201710159699 A CN 201710159699A CN 107103917 A CN107103917 A CN 107103917A
- Authority
- CN
- China
- Prior art keywords
- audio frame
- energy
- frame
- current audio
- current
- 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
- 230000033764 rhythmic process Effects 0.000 title claims abstract description 104
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000001228 spectrum Methods 0.000 claims abstract description 62
- 230000009466 transformation Effects 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000000034 method Methods 0.000 abstract description 7
- 230000000694 effects Effects 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 238000005314 correlation function Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 241001413866 Diaphone Species 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L25/81—Detection of presence or absence of voice signals for discriminating voice from music
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/03—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the type of extracted parameters
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/78—Detection of presence or absence of voice signals
- G10L2025/783—Detection of presence or absence of voice signals based on threshold decision
Landscapes
- Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Auxiliary Devices For Music (AREA)
- Electrophonic Musical Instruments (AREA)
Abstract
The invention discloses a kind of music rhythm detection method and its system, method includes：Obtain the voice data of music；An audio frame is sequentially obtained in the voice data as current audio frame, by the spectrum energy of current audio frame and a upper audio frame and difference, as current audio frame energy differences and preserve the energy differences；Determine the corresponding energy threshold of current audio frame；The energy differences of current audio frame and its continuous audio frame of two or more adjacent thereto before are obtained, the energy differences of the audio frame of more than three are obtained；If there is peak value in the energy differences of the audio frame of described more than three, and the peak value is more than the corresponding energy threshold of current audio frame, then the corresponding audio frame of the peak value is labeled as into rhythm point.The present invention can accurately and rapidly detect the position of rhythm point in music, and strong adaptability.
Description
Technical field
The present invention relates to voice data processing technology field, more particularly to a kind of music rhythm detection method and its system.
Background technology
Hand-guided, extremely labor intensive are carried out using DMX consoles mostly to the control of light in majority stage at present
Cost, audio frequency control lighting technology, which mainly replaces, manually to be detected the rhythm of song in real time by software and controls light.And show
There is audio frequency control lighting technology not high and adaptability is not strong for the accuracy in detection of song rhythm, it is difficult to reach music with light
The purpose of intelligent interaction.
In Publication No. CN201210477064.1 Chinese patent open file, it discloses a kind of inspection of music rhythm
Survey method and detection means, wherein music rhythm detection method include：Obtain the audio signal for being detected music；Calculate and be detected
Cross-correlation function between the audio signal of music and the audio signal of default music rhythm model；According to detected music
Each crest location of type and cross-correlation function curve obtains being detected bag in music being detected the number of times occurred in music
The quantity of the default music rhythm model contained；And by the quantity of the default music rhythm model included in detected music
It is compared with default cadence information and determines to be detected the rhythm of music.The documents are by pre-establishing music rhythm mould
Type, so as to obtain the correlation function of detected audio signal, and then obtains the rhythm for being detected audio.Using this detection side
Method, need to be obtained ahead of time voice data, and carry out setting up music rhythm model, increase detecting step and complexity, to practical application
Make troubles.
The content of the invention
The technical problems to be solved by the invention are：A kind of music rhythm detection method and its system are proposed, inspection can be improved
Survey efficiency and accuracy rate.
In order to solve the above-mentioned technical problem, the technical solution adopted by the present invention is：A kind of music rhythm detection method, bag
Include：
Obtain the voice data of music；
An audio frame is sequentially obtained in the voice data as current audio frame, by current audio frame and a upper audio
The difference of the spectrum energy sum of frame, as current audio frame energy differences and preserve the energy differences；
Determine the corresponding energy threshold of current audio frame；
The energy differences of current audio frame and its continuous audio frame of two or more adjacent thereto before are obtained, are obtained
The energy differences of the audio frame of more than three；
If there is peak value in the energy differences of the audio frame of described more than three, and the peak value is more than current audio frame pair
The energy threshold answered, then be labeled as rhythm point by the corresponding audio frame of the peak value.
The invention further relates to a kind of music rhythm detecting system, including：
First acquisition module, the voice data for obtaining music；
Second acquisition module, ought for sequentially obtaining an audio frame in the voice data as current audio frame
The spectrum energy of preceding audio frame and a upper audio frame and difference, as current audio frame energy differences and preserve the energy
Difference；
Determining module, for determining the corresponding energy threshold of current audio frame；
3rd acquisition module, two or more adjacent thereto for acquisition current audio frame and its before is continuous
The energy differences of audio frame, obtain the energy differences of the audio frame of more than three；
Mark module, if there is peak value in energy differences for the audio frame of described more than three, and the peak value is big
In the corresponding energy threshold of current audio frame, then the corresponding audio frame of the peak value is labeled as rhythm point.
The beneficial effects of the present invention are：The rhythm in voice data is detected according to the energy differences between audio frame
Point, can be carried out, with higher accuracy in real time；And model need not be set up, pass through several adjacent audio frames of com-parison and analysis
Energy differences, determine rhythm point, improve detection efficiency；Energy is adaptively adjusted according to the energy differences of processed audio frame
Threshold value so that energy threshold is more matched with currently processed voice data, it is to avoid the rhythm point detected is too little or too much, enters
One step improves the accuracy of detection, the rhythm detection of all kinds music is applicable to, with stronger adaptability, robustness
By force.
Brief description of the drawings
Fig. 1 is a kind of flow chart of music rhythm detection method of the invention；
Fig. 2 is the method flow diagram of the embodiment of the present invention one；
Fig. 3 is the step S2 of the embodiment of the present invention one method flow diagram；
Fig. 4 is the step S3 of the embodiment of the present invention two method flow diagram；
Fig. 5 is a kind of structural representation of music rhythm detecting system of the invention；
Fig. 6 is the system structure diagram of the embodiment of the present invention three.
Label declaration：
1st, the first acquisition module；2nd, the second acquisition module；3rd, determining module；4th, the 3rd acquisition module；
5th, mark module；6th, module is continued executing with；7th, control module；
21st, first acquisition unit；22nd, first unit is obtained；23rd, the 4th computing unit；24th, second acquisition unit；25th,
Two obtain unit；26th, the 5th computing unit；27th, the 3rd unit is obtained；
31st, the first setting unit；32nd, the first computing unit；33rd, the second setting unit；
321st, the second computing unit；322nd, the 3rd computing unit.
Embodiment
To describe technology contents, the objects and the effects of the present invention in detail, below in conjunction with embodiment and coordinate attached
Figure is explained in detail.
The design of most critical of the present invention is：Rhythm point is determined according to energy differences, meanwhile, audio frame correspondence is determined in real time
Energy threshold.
Referring to Fig. 1, a kind of music rhythm detection method, including：
Obtain the voice data of music；
An audio frame is sequentially obtained in the voice data as current audio frame, by current audio frame and a upper audio
The difference of the spectrum energy sum of frame, as current audio frame energy differences and preserve the energy differences；
Determine the corresponding energy threshold of current audio frame；
The energy differences of current audio frame and its continuous audio frame of two or more adjacent thereto before are obtained, are obtained
The energy differences of the audio frame of more than three；
If there is peak value in the energy differences of the audio frame of described more than three, and the peak value is more than current audio frame pair
The energy threshold answered, then be labeled as rhythm point by the corresponding audio frame of the peak value.
It was found from foregoing description, the beneficial effects of the present invention are：The rhythm of voice data can be detected in real time, examined
The degree of accuracy for surveying result is high, and efficiency high.
Further, described " determining the corresponding energy threshold of current audio frame " is specially：
If the corresponding sequence number of the current audio frame sequentially obtained is less than or equal to default frame number N, by current audio frame pair
The energy threshold answered is set to default first energy threshold；
If the corresponding serial number of the current audio frame sequentially obtained presets frame number N natural several times, according to the first audio
The energy differences of each audio frame in frame group, calculating obtains the second energy threshold, and the first audio frame group includes current audio frame
And its continuous N-1 audio frame adjacent thereto before；
The corresponding energy threshold of continuous N number of audio frame adjacent thereto after current audio frame is set to described second
Energy threshold.
Further, described " if the corresponding serial number of the current audio frame sequentially obtained presets frame number N natural several times,
Then according to the energy differences of each audio frame in the first audio frame group, calculating obtains the second energy threshold " be specially：
If the corresponding serial number of the current audio frame sequentially obtained presets frame number N natural several times, according to the first audio
The energy differences of each audio frame in frame group, calculate the average value and intermediate value for obtaining the energy differences；
According to the average value and intermediate value, calculating obtains the second energy threshold.
Further, described " according to the average value and intermediate value, calculating obtains the second energy threshold " is specially：
Calculated according to formula δ=α × mean+ β × median+ γ and obtain the second energy threshold, wherein, mean is described flat
Average, median is the intermediate value, and α is the weight of the correspondence average value, and β is the weight of the correspondence intermediate value, and γ is default
Constant.
Seen from the above description, according to the situation of the energy differences of the audio frame of certain frame number, real-time update audio frame pair
Energy threshold is answered, strong robustness has stronger adaptability to the rhythm detection of different type song.
Further, described " if there is peak value in the energy differences of the audio frame of described more than three, and the peak value is big
In the corresponding energy threshold of current audio frame, then the corresponding audio frame of the peak value is labeled as rhythm point " be specially：Work as acquisition
Audio frame energy differences quantity be three when, if the energy differences of three audio frames meet Dn-2<Dn-1And Dn-1>Dn,
While Dn-1>δn, then by Dn-1Corresponding audio frame is labeled as rhythm point；Wherein, δnFor the corresponding energy threshold of current audio frame,
DnFor the energy differences of current audio frame, Dn-1For the energy differences of the adjacent previous audio frame of current audio frame, Dn-2For current sound
The energy differences of adjacent preceding two audio frame of frequency frame.
Further, it is described " audio frame sequentially to be obtained in the voice data as current audio frame, by current sound
The spectrum energy of frequency frame and a upper audio frame and difference, as current audio frame energy differences and preserve the energy difference
Value " is specially：
According to default frame length, first audio frame of the voice data is obtained；
Fourier transformation is carried out to first audio frame, the frequency spectrum of first audio frame is obtained；
Calculate obtain the frequency spectrum of first audio frame in the spectrum energy of default frequency range and；
According to default frame length, next audio frame of the voice data is obtained, current audio frame is used as；
Fourier transformation is carried out to current audio frame, the frequency spectrum of current audio frame is obtained；
Calculate obtain the frequency spectrum of the current audio frame in the spectrum energy of default frequency range and；
By the spectrum energy of current audio frame and subtract a upper audio frame spectrum energy and, obtain current audio frame
Energy differences, and preserve the energy differences.
Further, after described " the corresponding audio frame of the peak value is labeled as into rhythm point ", further comprise：
Continue executing with described according to default frame length, obtain next audio frame of the voice data, be used as current sound
The step of frequency frame.
Further, after described " the corresponding audio frame of the peak value is labeled as into rhythm point ", further comprise：
External equipment linkage is controlled according to the rhythm point, or according to rhythm point and its spectrum energy of corresponding audio frame
With the displaying voice data.
Seen from the above description, detect to apply to after rhythm point the control of external equipment, the control of such as light of stage,
Music and the effect of light intelligent interaction can be achieved；By showing the corresponding audio frequency characteristics of rhythm point, user is set intuitively to find out
The corresponding tempo variation of the voice data.
Fig. 5 is refer to, the present invention also proposes a kind of music rhythm detecting system, including：
First acquisition module, the voice data for obtaining music；
Second acquisition module, ought for sequentially obtaining an audio frame in the voice data as current audio frame
The spectrum energy of preceding audio frame and a upper audio frame and difference, as current audio frame energy differences and preserve the energy
Difference；
Determining module, for determining the corresponding energy threshold of current audio frame；
3rd acquisition module, two or more adjacent thereto for acquisition current audio frame and its before is continuous
The energy differences of audio frame, obtain the energy differences of the audio frame of more than three；
Mark module, if there is peak value in energy differences for the audio frame of described more than three, and the peak value is big
In the corresponding energy threshold of current audio frame, then the corresponding audio frame of the peak value is labeled as rhythm point.
Further, the determining module includes：
First setting unit, if the corresponding sequence number of current audio frame for sequentially obtaining is less than or equal to default frame number N,
The corresponding energy threshold of current audio frame is then set to default first energy threshold；
First computing unit, if the corresponding serial number of current audio frame for sequentially obtaining presets frame number N natural number
Times, then according to the energy differences of each audio frame in the first audio frame group, calculating obtains the second energy threshold, first audio frame
Group includes current audio frame and its continuous N-1 audio frame adjacent thereto before；
Second setting unit, for by the corresponding energy of continuous N number of audio frame adjacent thereto after current audio frame
Threshold value is set to second energy threshold.
Further, first computing unit includes：
Second computing unit, if the corresponding serial number of current audio frame for sequentially obtaining presets frame number N natural number
Times, then according to the energy differences of each audio frame in the first audio frame group, calculate the average value and intermediate value for obtaining the energy differences；
3rd computing unit, for according to the average value and intermediate value, calculating to obtain the second energy threshold.
Further, the 3rd computing unit according to formula δ=α × mean+ β × median+ γ specifically for calculating
The second energy threshold is obtained, wherein, mean is the average value, and median is the intermediate value, and α is the power of the correspondence average value
Weight, β is the weight of the correspondence intermediate value, and γ is default constant.
Further, when the mark module is three specifically for the quantity of the energy differences of the audio frame when acquisition, if
The energy differences of three audio frames meet Dn-2<Dn-1And Dn-1>Dn, while Dn-1>δn, then by Dn-1Corresponding audio frame flag
For rhythm point；Wherein, δnFor the corresponding energy threshold of current audio frame, DnFor the energy differences of current audio frame, Dn-1To be current
The energy differences of the adjacent previous audio frame of audio frame, Dn-2For the energy differences of adjacent preceding two audio frame of current audio frame.
Further, second acquisition module includes：
First acquisition unit, for according to default frame length, obtaining first audio frame of the voice data；
First obtains unit, for carrying out Fourier transformation to first audio frame, obtains the frequency spectrum of first audio frame；
4th computing unit, spectrum energy of the frequency spectrum in default frequency range of first audio frame is obtained for calculating
With；
Second acquisition unit, for according to default frame length, obtaining next audio frame of the voice data, as working as
Preceding audio frame；
Second obtains unit, for carrying out Fourier transformation to current audio frame, obtains the frequency spectrum of current audio frame；
5th computing unit, for calculate obtain the frequency spectrum of the current audio frame in the spectrum energy of default frequency range and；
3rd obtains unit, for by the spectrum energy of current audio frame and the spectrum energy for subtracting a upper audio frame
With obtain the energy differences of current audio frame, and preserve the energy differences.
Further, in addition to：
Module is continued executing with, it is described according to default frame length for continuing executing with, obtain the next of the voice data
Audio frame, the step of as current audio frame.
Further, in addition to：
Control module, for controlling external equipment linkage according to the rhythm point, or according to rhythm point and its corresponding sound
The spectrum energy and the displaying voice data of frequency frame.
Embodiment one
Fig. 2 is refer to, embodiments of the invention one are：A kind of music rhythm detection method, comprises the following steps：
S1：Obtain the voice data of music；Further, voice data is normalized place after acquisition voice data
Reason.The music includes song and accompaniment.
S2：An audio frame is sequentially obtained in the voice data as current audio frame, by current audio frame and upper one
The difference of the spectrum energy sum of audio frame, is used as the energy differences D of current audio framenAnd preserve the energy differences Dn；
S3：Determine the corresponding energy threshold δ of current audio framen；In the present embodiment, the energy threshold can be pre- for one
If empirical value, meanwhile, the corresponding energy threshold of each audio frame is identical in the present embodiment, is the default empirical value.
S4：Obtain current audio frame and its continuous audio frame of two or more adjacent thereto before, obtain three with
On audio frame energy differences；
S5：Judge described more than three audio frame energy differences in whether there is peak value, and the peak value be more than work as
The corresponding energy threshold of preceding audio frame, if so, then performing step S6.For example, when the energy differences of three audio frames of acquisition, i.e.,
Judge whether to meet following conditions：Dn-2<Dn-1And Dn-1>Dn, meanwhile, Dn-1>δn, wherein, Dn-1It is adjacent previous for current audio frame
The energy differences of audio frame, Dn-2For the energy differences of adjacent preceding two audio frame of current audio frame.
S6：The corresponding audio frame of the peak value is labeled as rhythm point.Return and perform step S2, until voice data processing
Finish.
Wherein, as shown in figure 3, step S2 comprises the following steps：
S201：According to default frame length, first audio frame of the voice data is obtained；Further, according to difference
Sample rate set corresponding frame length, for example, sample rate is 44.1khz, frame length is 1024.
S202：Fourier transformation is carried out to first audio frame, the frequency spectrum of first audio frame is obtained；
S203：Calculate obtain the frequency spectrum of first audio frame in the spectrum energy of default frequency range and；Band limits can
Choose according to demand, such as low frequency part, intermediate-frequency section, HFS, can also full frequency band, the present embodiment is in full range segment limit
The sum of spectrum energy is inside asked for, S is usednRepresent, subscript n represents frame number, started counting up from 1, i.e. the corresponding sequence number of audio frame.
S204：According to default frame length, next audio frame of the voice data is obtained, current audio frame is used as；
S205：Fourier transformation is carried out to current audio frame, the frequency spectrum of current audio frame is obtained；
S206：Calculate obtain the frequency spectrum of the current audio frame in the spectrum energy of default frequency range and；
S207：By the spectrum energy of current audio frame and subtract a upper audio frame spectrum energy and, obtain current sound
The energy differences of frequency frame, and preserve the energy differences.Specifically, according to formula Dn=Sn-Sn-1Calculate current audio frame relative
The energy differences of a upper audio frame.Wherein, it can be neglected for the energy differences of first audio frame, also can be directly by first sound
The spectral energy values of frequency frame are used as its energy differences.
Further, returned after step S6 and perform step S204.
Preferably, after step S6, in addition to：External equipment linkage is controlled according to the rhythm point, or according to rhythm point
And its spectrum energy of corresponding audio frame and the displaying voice data.
The rhythm point control external equipment linkage includes being controlled light according to rhythm point.Can be specifically：a、
One rhythm point of correspondence flashes a kind of lamp of color；B, a type of lamp (such as shot-light) of flicker；C, one rhythm point of correspondence
The lamp of two or more colors is flashed successively；D, the polytype lamp of one rhythm point of correspondence coordinate flicker；E, one section of correspondence
Play and a little coordinate water spray, jet while light flash, scream or applause effect so that the display of light coordinates the change of rhythm point
Change and change.
The spectrum energy according to rhythm point and its corresponding audio frame and the displaying voice data can be：
The voice data is shown using electrocardiogram, wherein, the potential change of electrocardiogram represents the rhythm point diaphone
The change of the spectrum energy sum of frequency frame, the speed of potential change represents the speed that the rhythm point occurs；
Or the voice data is shown using the sound column figure moved left and right, wherein, the length of sound column represents the rhythm
The spectrum energy of point correspondence audio frame and, the speed of sound column movement represents the speed that the rhythm point occurs；
Or the voice data is shown using the sound column figure of eustasy, wherein, the soaring height of sound column represents described
Rhythm point corresponds to the spectrum energy of audio frame and the lifting speed of sound column represents the speed that the rhythm point occurs.
The present embodiment detects the rhythm point in voice data according to the energy differences between audio frame, can enter in real time
OK, with higher accuracy；And need not set up model, by the energy differences of several adjacent audio frames of com-parison and analysis, really
Rhythm point is made, detection efficiency is improved.Detect to apply to after rhythm point the control of external equipment, the control of such as light of stage
System, can be achieved music and the effect of light intelligent interaction；By showing the corresponding audio frequency characteristics of rhythm point, user is set intuitively to see
Go out the corresponding tempo variation of the voice data.
Embodiment two
The present embodiment is the further expansion of embodiment one, and something in common is not repeated, and difference is, in step s3,
Energy threshold is not fixed.
As shown in figure 4, step S3 comprises the following steps：
S301：Judge whether the corresponding sequence number of current audio frame sequentially obtained is less than or equal to default frame number N, if so,
Step S302 is then performed, if it is not, then performing step S303.
S302：The corresponding energy threshold of current audio frame is set to default first energy threshold；
S303：Whether judge the corresponding sequence number of current audio frame sequentially obtained is the natural several times for presetting frame number N, if
It is then to perform step S304.The corresponding sequence number of the current audio frame sequentially obtained is obtained, and judges whether the sequence number can be whole
Except default first frame number.
S304：According to the energy differences of each audio frame in the first audio frame group, calculating obtains the second energy threshold, and described the
Adjacent thereto continuous N-1 audio frame of the one audio frame group including current audio frame and its before.Obtain current audio frame
And its energy differences of continuous N-1 audio frame adjacent thereto before；According to the energy differences, calculating obtains the energy
Measure the average value and intermediate value of difference；According to the average value and intermediate value, calculating obtains the second energy threshold.Specifically, according to
Formula δ=α × mean+ β × median+ γ are calculated and are obtained the second energy threshold, wherein, mean is the average value, median
For the intermediate value, α is the weight of the correspondence average value, and β is the weight of the correspondence intermediate value, and γ is default constant.
S305：The corresponding energy threshold of continuous N number of audio frame adjacent thereto after current audio frame is set to institute
State the second energy threshold.
For example, it is assumed that default frame number N is 150 frames, then preceding 150 frame in voice data, i.e. the 1st frame to the 150th frame are corresponding
Energy threshold be default first energy threshold；Meanwhile, when traversing 150 frame, its sequence number is also for default frame number N's
Natural several times, therefore, obtain the energy differences of the 150th frame and its continuous 149 frame adjacent thereto before, namely the 1st frame is extremely
The energy differences of 150th frame, calculate the average value and intermediate value of the energy differences of this 150 frame, then obtain by weighted calculation
Two energy thresholds, and using the second energy threshold as continuous 150 frame adjacent thereto after the 150th frame audio frame, namely
The corresponding energy threshold of 151st frame to the 300th frame.Similarly, when traversing 300 frame, then according to the 151st frame to the 300th frame
Energy differences, calculate the corresponding energy threshold of the 301st frame to the 450th frame, by that analogy.
The energy range of different songs is simultaneously differed, and the different phase energy range of same song may also have deviation,
Therefore a uniform threshold adaptability is only set not strong, if threshold value is bigger than normal, the rhythm point missing detected, if threshold value
Less than normal, then the rhythm point detected is unnecessary.The present embodiment proposes a kind of method of threshold adaptive, according to processed audio frame
Energy differences adjustment energy threshold so that energy threshold is more matched with currently processed voice data, it is to avoid detected
Rhythm point is too little or too much, further increases the accuracy of detection, is applicable to the rhythm detection of all kinds music, has
Stronger adaptability, strong robustness.
Embodiment three
Fig. 6 is refer to, the present embodiment is a kind of music rhythm detecting system of correspondence above-described embodiment, including：
First acquisition module 1, the voice data for obtaining music；
Second acquisition module 2, ought for sequentially obtaining an audio frame in the voice data as current audio frame
The spectrum energy of preceding audio frame and a upper audio frame and difference, as current audio frame energy differences and preserve the energy
Difference；
Determining module 3, for determining the corresponding energy threshold of current audio frame；
3rd acquisition module 4, two or more adjacent thereto for acquisition current audio frame and its before is continuous
Audio frame energy differences, obtain the energy differences of the audio frame of more than three；
Mark module 5, if there is peak value in energy differences for the audio frame of described more than three, and the peak value is big
In the corresponding energy threshold of current audio frame, then the corresponding audio frame of the peak value is labeled as rhythm point.
Further, the determining module 3 includes：
First setting unit 31, if the corresponding sequence number of current audio frame for sequentially obtaining is less than or equal to default frame number
N, then be set to default first energy threshold by the corresponding energy threshold of current audio frame；
First computing unit 32, if the corresponding serial number of current audio frame for sequentially obtaining presets frame number N nature
Several times, then according to the energy differences of each audio frame in the first audio frame group, calculating obtains the second energy threshold, first audio
Adjacent thereto continuous N-1 audio frame of the frame group including current audio frame and its before；
Second setting unit 33, for by the corresponding energy of continuous N number of audio frame adjacent thereto after current audio frame
Amount threshold value is set to second energy threshold.
Further, first computing unit 32 includes：
Second computing unit 321, if the corresponding serial number of current audio frame for sequentially obtaining presets frame number N nature
Several times, then according to the energy differences of each audio frame in the first audio frame group, calculate the average value for obtaining the energy differences with
Value；
3rd computing unit 322, for according to the average value and intermediate value, calculating to obtain the second energy threshold.
Further, the 3rd computing unit 322 according to formula δ=α × mean+ β × median+ γ specifically for counting
Calculation obtains the second energy threshold, wherein, mean is the average value, and median is the intermediate value, and α is the correspondence average value
Weight, β is the weight of the correspondence intermediate value, and γ is default constant.
Further, when the mark module 5 is three specifically for the quantity of the energy differences of the audio frame when acquisition, if
The energy differences of three audio frames meet Dn-2<Dn-1And Dn-1>Dn, while Dn-1>δn, then by Dn-1Corresponding audio frame flag
For rhythm point；Wherein, δnFor the corresponding energy threshold of current audio frame, DnFor the energy differences of current audio frame, Dn-1To be current
The energy differences of the adjacent former frame of audio frame, Dn-2For the energy differences of the adjacent front cross frame of current audio frame.
Further, second acquisition module 2 includes：
First acquisition unit 21, for according to default frame length, obtaining first audio frame of the voice data；
First obtains unit 22, for carrying out Fourier transformation to first audio frame, obtains the frequency of first audio frame
Spectrum；
4th computing unit 23, spectrum energy of the frequency spectrum in default frequency range of first audio frame is obtained for calculating
With；
Second acquisition unit 24, for according to default frame length, obtaining next audio frame of the voice data, as
Current audio frame；
Second obtains unit 25, for carrying out Fourier transformation to current audio frame, obtains the frequency spectrum of current audio frame；
5th computing unit 26, spectrum energy of the frequency spectrum in default frequency range of the current audio frame is obtained for calculating
With；
3rd obtains unit 27, for by the spectrum energy of current audio frame and the spectrum energy for subtracting a upper audio frame
With obtain the energy differences of current audio frame, and preserve the energy differences.
Further, in addition to：
Module 6 is continued executing with, it is described according to default frame length for continuing executing with, obtain the next of the voice data
Audio frame, the step of as current audio frame.
Further, in addition to：
Control module 7, for controlling external equipment linkage according to the rhythm point, or according to rhythm point and its corresponding sound
The spectrum energy and the displaying voice data of frequency frame.
In summary, the present invention is provided a kind of music rhythm detection method and its system, according to the energy between audio frame
Measure difference to detect the point of the rhythm in voice data, can carry out in real time, with higher accuracy；According to processed audio frame
Energy differences adaptively adjust energy threshold so that energy threshold is more matched with currently processed voice data, it is to avoid inspection
The rhythm point measured is too little or too much, further increases the accuracy of detection, is applicable to the rhythm inspection of all kinds music
Survey, with stronger adaptability, strong robustness；Detect to apply to after rhythm point the control of external equipment, such as light of stage
Control, the effect of music and light intelligent interaction can be achieved；By showing the corresponding audio frequency characteristics of rhythm point, make user straight
Watch out the corresponding tempo variation of the voice data.
Embodiments of the invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize this hair
The equivalents that bright specification and accompanying drawing content are made, or the technical field of correlation is directly or indirectly used in, similarly include
In the scope of patent protection of the present invention.
Claims (12)
1. a kind of music rhythm detection method, it is characterised in that including：
Obtain the voice data of music；
An audio frame is sequentially obtained in the voice data as current audio frame, by current audio frame and a upper audio frame
The difference of spectrum energy sum, as current audio frame energy differences and preserve the energy differences；
Determine the corresponding energy threshold of current audio frame；
The energy differences of current audio frame and its continuous audio frame of two or more adjacent thereto before are obtained, three are obtained
The energy differences of audio frame above；
If there is peak value in the energy differences of the audio frame of described more than three, and the peak value is corresponding more than current audio frame
Energy threshold, then be labeled as rhythm point by the corresponding audio frame of the peak value.
2. music rhythm detection method according to claim 1, it is characterised in that described " to determine current audio frame correspondence
Energy threshold " be specially：
If the corresponding sequence number of the current audio frame sequentially obtained is less than or equal to default frame number N, and current audio frame is corresponding
Energy threshold is set to default first energy threshold；
If the corresponding serial number of the current audio frame sequentially obtained presets frame number N natural several times, according to the first audio frame group
In each audio frame energy differences, calculating obtains the second energy threshold, the first audio frame group include current audio frame and its
Continuous N-1 audio frame adjacent thereto before；
The corresponding energy threshold of continuous N number of audio frame adjacent thereto after current audio frame is set to second energy
Threshold value.
3. music rhythm detection method according to claim 2, it is characterised in that described " if the current sound sequentially obtained
The corresponding serial number of frequency frame presets frame number N natural several times, then according to the energy differences of each audio frame in the first audio frame group, meter
Calculation obtains the second energy threshold " be specially：
If the corresponding serial number of the current audio frame sequentially obtained presets frame number N natural several times, according to the first audio frame group
In each audio frame energy differences, calculate and obtain the average value and intermediate value of the energy differences；
According to the average value and intermediate value, calculating obtains the second energy threshold.
4. music rhythm detection method according to claim 3, it is characterised in that described " according to the average value with
Value, calculating obtains the second energy threshold " be specially：
Calculated according to formula δ=α × mean+ β × median+ γ and obtain the second energy threshold, wherein, mean is described average
Value, median is the intermediate value, and α is the weight of the correspondence average value, and β is the weight of the correspondence intermediate value, and γ is default
Constant.
5. music rhythm detection method according to claim 1, it is characterised in that described " if the sound of described more than three
There is peak value in the energy differences of frequency frame, and the peak value is more than the corresponding energy threshold of current audio frame, then by the peak value
Corresponding audio frame is labeled as rhythm point " be specially：When the quantity of the energy differences of the audio frame of acquisition is three, if described three
The energy differences of individual audio frame meet Dn-2<Dn-1And Dn-1>Dn, while Dn-1>δn, then by Dn-1Corresponding audio frame is labeled as rhythm
Point；Wherein, δnFor the corresponding energy threshold of current audio frame, DnFor the energy differences of current audio frame, Dn-1For current audio frame
The energy differences of adjacent previous audio frame, Dn-2For the energy differences of adjacent preceding two audio frame of current audio frame.
6. music rhythm detection method according to claim 1, it is characterised in that it is described " in the voice data according to
Sequence obtains an audio frame as current audio frame, by the spectrum energy of current audio frame and a upper audio frame and difference, as
The energy differences of current audio frame simultaneously preserve the energy differences " be specially：
According to default frame length, first audio frame of the voice data is obtained；
Fourier transformation is carried out to first audio frame, the frequency spectrum of first audio frame is obtained；
Calculate obtain the frequency spectrum of first audio frame in the spectrum energy of default frequency range and；
According to default frame length, next audio frame of the voice data is obtained, current audio frame is used as；
Fourier transformation is carried out to current audio frame, the frequency spectrum of current audio frame is obtained；
Calculate obtain the frequency spectrum of the current audio frame in the spectrum energy of default frequency range and；
By the spectrum energy of current audio frame and subtract a upper audio frame spectrum energy and, obtain the energy of current audio frame
Difference, and preserve the energy differences.
7. music rhythm detection method according to claim 6, it is characterised in that described " by the corresponding sound of the peak value
Frequency frame flag is rhythm point " after, further comprise：
Continue executing with described according to default frame length, obtain next audio frame of the voice data, be used as current audio frame
The step of.
8. music rhythm detection method according to claim 1, it is characterised in that described " by the corresponding sound of the peak value
Frequency frame flag is rhythm point " after, further comprise：
External equipment linkage is controlled according to the rhythm point, or according to spectrum energy and the exhibition of rhythm point and its corresponding audio frame
Show the voice data.
9. a kind of music rhythm detecting system, it is characterised in that including：
First acquisition module, the voice data for obtaining music；
Second acquisition module, for sequentially obtaining an audio frame in the voice data as current audio frame, by current sound
The spectrum energy of frequency frame and a upper audio frame and difference, as current audio frame energy differences and preserve the energy difference
Value；
Determining module, for determining the corresponding energy threshold of current audio frame；
3rd acquisition module, the continuous audio of two or more adjacent thereto for acquisition current audio frame and its before
The energy differences of frame, obtain the energy differences of the audio frame of more than three；
Mark module, if there is peak value in energy differences for the audio frame of described more than three, and the peak value is more than and worked as
The corresponding energy threshold of preceding audio frame, then be labeled as rhythm point by the corresponding audio frame of the peak value.
10. music rhythm detecting system according to claim 9, it is characterised in that the determining module includes：
First setting unit, will if the corresponding sequence number of current audio frame for sequentially obtaining is less than or equal to default frame number N
The corresponding energy threshold of current audio frame is set to default first energy threshold；
First computing unit, if the corresponding serial number of current audio frame for sequentially obtaining presets frame number N natural several times,
According to the energy differences of each audio frame in the first audio frame group, calculating obtains the second energy threshold, the first audio frame group bag
Include current audio frame and its continuous N-1 audio frame adjacent thereto before；
Second setting unit, for by the corresponding energy threshold of continuous N number of audio frame adjacent thereto after current audio frame
It is set to second energy threshold.
11. music rhythm detecting system according to claim 10, it is characterised in that first computing unit includes：
Second computing unit, if the corresponding serial number of current audio frame for sequentially obtaining presets frame number N natural several times,
According to the energy differences of each audio frame in the first audio frame group, the average value and intermediate value for obtaining the energy differences are calculated；
3rd computing unit, for according to the average value and intermediate value, calculating to obtain the second energy threshold.
12. music rhythm detecting system according to claim 9, it is characterised in that also include：
Control module, for controlling external equipment linkage according to the rhythm point, or according to rhythm point and its corresponding audio frame
Spectrum energy and show the voice data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710159699.XA CN107103917B (en) | 2017-03-17 | 2017-03-17 | Music rhythm detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710159699.XA CN107103917B (en) | 2017-03-17 | 2017-03-17 | Music rhythm detection method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107103917A true CN107103917A (en) | 2017-08-29 |
| CN107103917B CN107103917B (en) | 2020-05-05 |
Family
ID=59675459
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710159699.XA Active CN107103917B (en) | 2017-03-17 | 2017-03-17 | Music rhythm detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107103917B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108038863A (en) * | 2018-01-29 | 2018-05-15 | 歌尔科技有限公司 | Image partition method and device |
| CN108111909A (en) * | 2017-12-15 | 2018-06-01 | 广州市百果园信息技术有限公司 | Method of video image processing and computer storage media, terminal |
| CN108259983A (en) * | 2017-12-29 | 2018-07-06 | 广州市百果园信息技术有限公司 | A kind of method of video image processing, computer readable storage medium and terminal |
| CN108259984A (en) * | 2017-12-29 | 2018-07-06 | 广州市百果园信息技术有限公司 | Method of video image processing, computer readable storage medium and terminal |
| CN108259925A (en) * | 2017-12-29 | 2018-07-06 | 广州市百果园信息技术有限公司 | Music gifts processing method, storage medium and terminal in net cast |
| CN108281157A (en) * | 2017-12-28 | 2018-07-13 | 广州市百果园信息技术有限公司 | The detection method of drum beat and computer storage media, terminal in music |
| CN108322802A (en) * | 2017-12-29 | 2018-07-24 | 广州市百果园信息技术有限公司 | Stick picture disposing method, computer readable storage medium and the terminal of video image |
| CN108319657A (en) * | 2018-01-04 | 2018-07-24 | 广州市百果园信息技术有限公司 | Detect method, storage medium and the terminal of strong rhythm point |
| CN110265057A (en) * | 2019-07-10 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Generate multimedia method and device, electronic equipment, storage medium |
| CN110688518A (en) * | 2019-10-12 | 2020-01-14 | 广州酷狗计算机科技有限公司 | Rhythm point determining method, device, equipment and storage medium |
| CN110753238A (en) * | 2019-10-29 | 2020-02-04 | 北京字节跳动网络技术有限公司 | Video processing method, device, terminal and storage medium |
| CN110853677A (en) * | 2019-11-20 | 2020-02-28 | 北京雷石天地电子技术有限公司 | Drumbeat beat recognition method and device for songs, terminal and non-transitory computer readable storage medium |
| CN110890083A (en) * | 2019-10-31 | 2020-03-17 | 北京达佳互联信息技术有限公司 | Audio data processing method and device, electronic equipment and storage medium |
| CN111081271A (en) * | 2019-11-29 | 2020-04-28 | 福建星网视易信息***有限公司 | Music rhythm detection method based on frequency domain and time domain and storage medium |
| CN111105769A (en) * | 2019-12-26 | 2020-05-05 | 广州酷狗计算机科技有限公司 | Method, device, equipment and storage medium for detecting intermediate frequency rhythm point of audio |
| CN111128100A (en) * | 2019-12-20 | 2020-05-08 | 网易（杭州）网络有限公司 | Rhythm point detection method and device and electronic equipment |
| CN111630590A (en) * | 2018-02-14 | 2020-09-04 | 字节跳动有限公司 | Method for generating music data |
| CN112261767A (en) * | 2020-10-23 | 2021-01-22 | 深圳市智岩科技有限公司 | Method, device and system for controlling lamp effect and storage medium |
| CN112435687A (en) * | 2020-11-25 | 2021-03-02 | 腾讯科技（深圳）有限公司 | Audio detection method and device, computer equipment and readable storage medium |
| CN112866732A (en) * | 2020-12-30 | 2021-05-28 | 广州方硅信息技术有限公司 | Music broadcasting method and device, equipment and medium thereof |
| CN112866770A (en) * | 2020-12-31 | 2021-05-28 | 北京奇艺世纪科技有限公司 | Equipment control method and device, electronic equipment and storage medium |
| CN113192531A (en) * | 2021-05-28 | 2021-07-30 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, terminal and storage medium for detecting whether audio is pure music audio |
| WO2023093333A1 (en) * | 2021-11-25 | 2023-06-01 | 歌尔股份有限公司 | Vibration signal generation method and apparatus, electronic device, and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5614687A (en) * | 1995-02-20 | 1997-03-25 | Pioneer Electronic Corporation | Apparatus for detecting the number of beats |
| CN1484116A (en) * | 2002-09-20 | 2004-03-24 | 红芯有限责任公司 | Beat number detector |
| US20050217461A1 (en) * | 2004-03-31 | 2005-10-06 | Chun-Yi Wang | Method for music analysis |
| CN106098081A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | The acoustic fidelity identification method of audio files and device |
-
2017
- 2017-03-17 CN CN201710159699.XA patent/CN107103917B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5614687A (en) * | 1995-02-20 | 1997-03-25 | Pioneer Electronic Corporation | Apparatus for detecting the number of beats |
| CN1484116A (en) * | 2002-09-20 | 2004-03-24 | 红芯有限责任公司 | Beat number detector |
| US20050217461A1 (en) * | 2004-03-31 | 2005-10-06 | Chun-Yi Wang | Method for music analysis |
| CN106098081A (en) * | 2016-06-01 | 2016-11-09 | 腾讯科技（深圳）有限公司 | The acoustic fidelity identification method of audio files and device |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108111909A (en) * | 2017-12-15 | 2018-06-01 | 广州市百果园信息技术有限公司 | Method of video image processing and computer storage media, terminal |
| CN108281157A (en) * | 2017-12-28 | 2018-07-13 | 广州市百果园信息技术有限公司 | The detection method of drum beat and computer storage media, terminal in music |
| CN108322802A (en) * | 2017-12-29 | 2018-07-24 | 广州市百果园信息技术有限公司 | Stick picture disposing method, computer readable storage medium and the terminal of video image |
| CN108259984A (en) * | 2017-12-29 | 2018-07-06 | 广州市百果园信息技术有限公司 | Method of video image processing, computer readable storage medium and terminal |
| CN108259925A (en) * | 2017-12-29 | 2018-07-06 | 广州市百果园信息技术有限公司 | Music gifts processing method, storage medium and terminal in net cast |
| CN108259983A (en) * | 2017-12-29 | 2018-07-06 | 广州市百果园信息技术有限公司 | A kind of method of video image processing, computer readable storage medium and terminal |
| CN108319657A (en) * | 2018-01-04 | 2018-07-24 | 广州市百果园信息技术有限公司 | Detect method, storage medium and the terminal of strong rhythm point |
| CN108319657B (en) * | 2018-01-04 | 2022-02-01 | 广州市百果园信息技术有限公司 | Method for detecting strong rhythm point, storage medium and terminal |
| CN108038863A (en) * | 2018-01-29 | 2018-05-15 | 歌尔科技有限公司 | Image partition method and device |
| CN108038863B (en) * | 2018-01-29 | 2021-02-19 | 歌尔科技有限公司 | Image segmentation method and device |
| CN111630590A (en) * | 2018-02-14 | 2020-09-04 | 字节跳动有限公司 | Method for generating music data |
| CN111630590B (en) * | 2018-02-14 | 2024-05-14 | 字节跳动有限公司 | Method for generating music data |
| US11887566B2 (en) | 2018-02-14 | 2024-01-30 | Bytedance Inc. | Method of generating music data |
| CN110265057A (en) * | 2019-07-10 | 2019-09-20 | 腾讯科技（深圳）有限公司 | Generate multimedia method and device, electronic equipment, storage medium |
| CN110265057B (en) * | 2019-07-10 | 2024-04-26 | 腾讯科技（深圳）有限公司 | Method and device for generating multimedia, electronic equipment and storage medium |
| CN110688518A (en) * | 2019-10-12 | 2020-01-14 | 广州酷狗计算机科技有限公司 | Rhythm point determining method, device, equipment and storage medium |
| CN110688518B (en) * | 2019-10-12 | 2024-05-24 | 广州酷狗计算机科技有限公司 | Determination method, device, equipment and storage medium for rhythm point |
| CN110753238A (en) * | 2019-10-29 | 2020-02-04 | 北京字节跳动网络技术有限公司 | Video processing method, device, terminal and storage medium |
| CN110890083A (en) * | 2019-10-31 | 2020-03-17 | 北京达佳互联信息技术有限公司 | Audio data processing method and device, electronic equipment and storage medium |
| CN110890083B (en) * | 2019-10-31 | 2022-09-02 | 北京达佳互联信息技术有限公司 | Audio data processing method and device, electronic equipment and storage medium |
| CN110853677A (en) * | 2019-11-20 | 2020-02-28 | 北京雷石天地电子技术有限公司 | Drumbeat beat recognition method and device for songs, terminal and non-transitory computer readable storage medium |
| CN110853677B (en) * | 2019-11-20 | 2022-04-26 | 北京雷石天地电子技术有限公司 | Drumbeat beat recognition method and device for songs, terminal and non-transitory computer readable storage medium |
| CN111081271A (en) * | 2019-11-29 | 2020-04-28 | 福建星网视易信息***有限公司 | Music rhythm detection method based on frequency domain and time domain and storage medium |
| CN111081271B (en) * | 2019-11-29 | 2022-09-06 | 福建星网视易信息***有限公司 | Music rhythm detection method based on frequency domain and time domain and storage medium |
| CN111128100A (en) * | 2019-12-20 | 2020-05-08 | 网易（杭州）网络有限公司 | Rhythm point detection method and device and electronic equipment |
| CN111128100B (en) * | 2019-12-20 | 2021-04-20 | 网易（杭州）网络有限公司 | Rhythm point detection method and device and electronic equipment |
| CN111105769B (en) * | 2019-12-26 | 2023-01-10 | 广州酷狗计算机科技有限公司 | Method, device, equipment and storage medium for detecting intermediate frequency rhythm point of audio |
| CN111105769A (en) * | 2019-12-26 | 2020-05-05 | 广州酷狗计算机科技有限公司 | Method, device, equipment and storage medium for detecting intermediate frequency rhythm point of audio |
| CN112261767A (en) * | 2020-10-23 | 2021-01-22 | 深圳市智岩科技有限公司 | Method, device and system for controlling lamp effect and storage medium |
| CN112435687A (en) * | 2020-11-25 | 2021-03-02 | 腾讯科技（深圳）有限公司 | Audio detection method and device, computer equipment and readable storage medium |
| CN112866732A (en) * | 2020-12-30 | 2021-05-28 | 广州方硅信息技术有限公司 | Music broadcasting method and device, equipment and medium thereof |
| CN112866770A (en) * | 2020-12-31 | 2021-05-28 | 北京奇艺世纪科技有限公司 | Equipment control method and device, electronic equipment and storage medium |
| CN112866770B (en) * | 2020-12-31 | 2023-12-05 | 北京奇艺世纪科技有限公司 | Equipment control method and device, electronic equipment and storage medium |
| CN113192531A (en) * | 2021-05-28 | 2021-07-30 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, terminal and storage medium for detecting whether audio is pure music audio |
| CN113192531B (en) * | 2021-05-28 | 2024-04-16 | 腾讯音乐娱乐科技（深圳）有限公司 | Method, terminal and storage medium for detecting whether audio is pure audio |
| WO2023093333A1 (en) * | 2021-11-25 | 2023-06-01 | 歌尔股份有限公司 | Vibration signal generation method and apparatus, electronic device, and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107103917B (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107103917A (en) | Music rhythm detection method and its system | |
| CN111081271B (en) | Music rhythm detection method based on frequency domain and time domain and storage medium | |
| US10492276B2 (en) | Lighting control device, lighting control method, and lighting control program | |
| CN102543052B (en) | A kind of method and apparatus analyzing music BPM | |
| CN105612428B (en) | Measurement of partial discharge equipment, method for measurement of partial discharge and recording medium | |
| CN104620313A (en) | Audio signal analysis | |
| CN106251249A (en) | A kind of construction informationization dynamic monitoring system | |
| CN105445812B (en) | A kind of human body sensor detection method and device | |
| CN106725450A (en) | QRS complex detection method | |
| CN103578478B (en) | Obtain the method and system of musical tempo information in real time | |
| CN105125199A (en) | Heart rate detection method and heart rate detection device | |
| JP6627482B2 (en) | Technique determination device | |
| CN103841401A (en) | Apparatus and method for correcting depth map for three-dimensional image | |
| CN109116196A (en) | A kind of power cable fault discharging sound intelligent identification Method | |
| CN102116876B (en) | Method for detecting spatial point target space-base on basis of track cataloguing model | |
| CN103549947A (en) | Real-time and accurate electrocardiographic wave drawing method of smartphone platforms | |
| CN104808055B (en) | A kind of digital measuring method of signal frequency | |
| US20100204016A1 (en) | System and method for editing walking procedure | |
| CN109100727A (en) | A method of using motion virtual identification of sound source sound source motion profile | |
| CN206108591U (en) | Elevator displacement precision correction system based on acceleration sensor | |
| JP5092876B2 (en) | Sound processing apparatus and program | |
| CN207996386U (en) | Force exerciser with check weighing, speed measuring function | |
| KR20000054784A (en) | system for tracking the movement of the multiple object using an Appearance Model Based on Temporal Color and controlling method therefore | |
| EP0367191A2 (en) | Automatic music transcription method and system | |
| CN101483736A (en) | Television set with spectrum display function |
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 |