CN106504762A - Bird community quantity survey system and method - Google Patents
Bird community quantity survey system and method Download PDFInfo
- Publication number
- CN106504762A CN106504762A CN201610969673.7A CN201610969673A CN106504762A CN 106504762 A CN106504762 A CN 106504762A CN 201610969673 A CN201610969673 A CN 201610969673A CN 106504762 A CN106504762 A CN 106504762A
- Authority
- CN
- China
- Prior art keywords
- voice
- speech
- point
- noise
- signal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000012545 processing Methods 0.000 claims abstract description 39
- 230000005540 biological transmission Effects 0.000 claims abstract description 26
- 238000000926 separation method Methods 0.000 claims abstract description 25
- 238000004891 communication Methods 0.000 claims description 12
- 238000001228 spectrum Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 11
- 230000009467 reduction Effects 0.000 claims description 11
- 238000001514 detection method Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 9
- 238000009432 framing Methods 0.000 claims description 9
- 230000036039 immunity Effects 0.000 claims description 4
- 238000011946 reduction process Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 2
- 238000010606 normalization Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000007613 environmental effect Effects 0.000 abstract description 4
- 238000012360 testing method Methods 0.000 abstract description 2
- XNCSCQSQSGDGES-UHFFFAOYSA-N 2-[2-[bis(carboxymethyl)amino]propyl-(carboxymethyl)amino]acetic acid Chemical compound OC(=O)CN(CC(O)=O)C(C)CN(CC(O)=O)CC(O)=O XNCSCQSQSGDGES-UHFFFAOYSA-N 0.000 description 4
- 238000012880 independent component analysis Methods 0.000 description 4
- 230000001360 synchronised effect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000002955 isolation Methods 0.000 description 2
- 238000007476 Maximum Likelihood Methods 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000005236 sound signal Effects 0.000 description 1
- 238000012546 transfer Methods 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
-
- 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
- G10L17/00—Speaker identification or verification techniques
- G10L17/26—Recognition of special voice characteristics, e.g. for use in lie detectors; Recognition of animal voices
-
- 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
- G10L19/00—Speech or audio signals analysis-synthesis techniques for redundancy reduction, e.g. in vocoders; Coding or decoding of speech or audio signals, using source filter models or psychoacoustic analysis
- G10L19/008—Multichannel audio signal coding or decoding using interchannel correlation to reduce redundancy, e.g. joint-stereo, intensity-coding or matrixing
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0272—Voice signal separating
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L2021/02087—Noise filtering the noise being separate speech, e.g. cocktail party
-
- 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
- G10L21/00—Speech or voice signal processing techniques to produce another audible or non-audible signal, e.g. visual or tactile, in order to modify its quality or its intelligibility
- G10L21/02—Speech enhancement, e.g. noise reduction or echo cancellation
- G10L21/0208—Noise filtering
- G10L21/0216—Noise filtering characterised by the method used for estimating noise
- G10L2021/02161—Number of inputs available containing the signal or the noise to be suppressed
- G10L2021/02166—Microphone arrays; Beamforming
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Human Computer Interaction (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computational Linguistics (AREA)
- Signal Processing (AREA)
- Quality & Reliability (AREA)
- Mathematical Physics (AREA)
- Circuit For Audible Band Transducer (AREA)
Abstract
The invention discloses a kind of bird community quantity survey system and method, are related to bird community protection and voice de-noising and separation technology field.The system includes apparatus for processing audio（10）, data transmission device（20）, terminal data processing device（30）And power supply（40）；Apparatus for processing audio（10）, data transmission device（20）With terminal data processing device（30）It is sequentially connected；Power supply（40）Respectively with apparatus for processing audio（10）And data transmission device（20）Connection.This method is：1. voice de-noising；2. speech Separation.The present invention is applied to the quantity of zoo, agricultural department and conservation of wildlife department more easily observability estimate birds；Also important reference is provided to environmental administration to evaluating and testing somewhere environmental rating.
Description
Technical field
The present invention relates to bird community protection and voice de-noising and separation technology field, more particularly to a kind of bird community
Quantity survey system and method.
Background technology
Currently, bird community protection is cut down in a large number because of vegetation, the continuous deterioration reason of ecological environment and interesting, effectively
Group's bird quantity statistics method is most important for bird community protection.Traditional method is more to count animal kind using marked recapture
The quantity of group, the method easily produce impact to the normal activities for affecting animal, and statistical accuracy is not enough.In recent years, use
Before application well is presented in terms of the speech Separation algorithm for estimating of field of voice signal is in voice identification, noise reduction
Scape.
Traditional voice de-noising algorithm has adaptive filter algorithm, spectrum-subtraction and Wiener Filter Method etc., using characteristic parameter
End-point detection is carried out, judge voice signal has words section and without words section, by without words section estimated noise spectrum, reaching speech enhan-cement
Purpose；In terms of speech Separation, Independent Component Analysis Algorithm（Independent Component Analysis, ICA）Including pole
Maximum-likelihood method of estimation, maximum entropy method, Minimum mutual information method, Higher-Order Cumulants etc., using signal after separation each
Between component, maximum independence to be setting up contrast function, by maximum or minimize contrast function and obtain separation matrix, reaches point
Purpose from source signal.Document points out that ICA algorithm is only used for the number of source signal less than or equal to received by sensor
In the case of the number of mixed signal, the estimation of bird community quantity is not suitable for.
Content of the invention
The purpose of the present invention is rested in the artificial traditional method using bird appreciation instrument for observation birds activity at present, is damaged
Consumption manpower and the again low problem of efficiency, there is provided a kind of bird community quantity survey system and method, so as to realize using right
The collection of bird community birds mixing voice and noise reduction, based on the birds mixing voice isolation technics of peak estimation, separate and mix
Voice can estimate birds number.
The mentality of designing of the present invention：
As the collection of voice in truth has the interference of noise, birds voice signal there may be error.In order to improve
The accuracy of speech Separation, the first mixing voice to gathering carry out noise reduction process；Human speech isolation technics are analogous to, in conjunction with
Birds phonetic feature, designs a kind of DUET Speech separation algorithms clustered based on PDTA；Sound attenuating is simultaneously taken account of, will be adopted
High-fidelity mike, strengthens voice signal.
For the needs of speech Separation, speech signal collection and processing system is initially set up, is realized to birds voice collecting,
A/D is changed；Secondly, the Transmission system of Speech processing is designed, it is contemplated that the verity of wild environment, we adopt channel radio
Letter technology, realizes Long-range Data Transmission；Next the operation such as the pretreatment to data, end-point detection is carried out at PC ends；Pre- place
Reason includes aliasing filtering, analog to digital conversion, framing adding window；End-point detection carries out end-point detection using the good Parameter Spectrum entropy of noise immunity,
Difference whether there is words section, estimates noise spectrum, carries out noise reduction using Wiener filtering；Finally, speech Separation is carried out to reducing noise of voice, we
Using a kind of DUET Speech separation algorithms clustered based on PDTA, separate voice number and be and estimate birds quantity number and extensive
Multiple source voice signal.
Specifically：
First, bird community quantity survey system（Abbreviation system）
The system includes apparatus for processing audio, data transmission device, terminal data processing device and power supply；
Its annexation is：
Apparatus for processing audio, data transmission device and terminal data processing device are sequentially connected；
Power supply is connected with apparatus for processing audio and data transmission device respectively.
2nd, bird community quantity survey method
This method includes two parts of voice de-noising and speech Separation.
1. voice de-noising
Birds mixing voice Y is gathered in the field environment using microphone array, framing adding window is carried out to the voice for gathering and is located in advance
Manage, extracting the good characteristic parameter spectrum entropy of noise immunity carries out end-point detection, judges there is words frame and without words frame noise, using Wiener filtering
Noise reduction algorithm carries out noise reduction process to the voice for gathering, and obtains pure birds voice；
2. speech Separation
Speech Separation is divided into peak estimation and source voice recovers two stages：
In the peak estimation stage, adding window, framing, Fourier transformation is carried out to clean speech, realize the rarefaction representation to gathering voice,
Pretreatment is carried out to rarefaction speech data again, is allowed on the upper semicircumference of speech data point chorologic unit circle, is asked each point to arrive（1,
0）Radian, region division is carried out to radian value, the probability density in each region is calculated, is obtained using local optimum resolving Algorithm close
Degree peak value, the number of peak value are the number for separating voice；
Source voice Restoration stage, finds the corresponding radian value of peak value, calculates hybrid matrix A, that is, need to solve Y=AX nonhomogeneous equations
Group, using DUET algorithms, is projected in each for mixing voice data point in all directions of hybrid matrix A, is sentenced according to projector distance
Which source voice class is fixed each data point belong to, you can recover each source voice X.
The present invention has the advantages that：
1. a kind of technical scheme of the voice de-noising based on improved Wiener filtering algorithm is provided
Framing adding window pretreatment is carried out to the voice for gathering, extracting the good characteristic parameter spectrum entropy of noise immunity carries out end-point detection,
Judge to have words frame with without words frame noise, noise reduction process is carried out to the voice for gathering using Wiener filtering noise reduction algorithm, is obtained pure
Birds voice.
2. the technical scheme of the Speech separation algorithm that a kind of combination DUET and PDTA is clustered is provided
Speech Separation is divided into peak estimation and recovers two stages with source voice.The peak estimation stage, clean speech is carried out adding window,
Framing, Fourier transformation, realize, to gathering the rarefaction representation of voice, then carrying out pretreatment to rarefaction speech data, allow voice
On the upper semicircumference of data point distribution unit circle, each point is asked to arrive（1,0）Radian, carry out region division to radian value, calculate
The probability density in each region, obtains density peaks using local optimum resolving Algorithm, and the number of peak value is and separates the individual of voice
Number.Source voice Restoration stage, finds the corresponding radian value of peak value, can calculate hybrid matrix A, that is, need to solve y=Ax nonhomogeneous equations
Group, using DUET algorithms, is projected in each for mixing voice data point in all directions of hybrid matrix A, is sentenced according to projector distance
Which source voice class is fixed each data point belong to, you can recover each source voice.
3. the technical scheme that a kind of bird community number based on speech Separation is estimated is provided
The method for breaking away from the bird community of original manual observation, using separating to mixing voice, the method for estimating source voice number
Reach to birds quantity survey.
4. it is applied to the quantity of zoo, agricultural department and conservation of wildlife department more easily observability estimate birds；
Also important reference is provided to environmental administration to evaluating and testing somewhere environmental rating.
Description of the drawings
Fig. 1 is the block diagram of the system；
Fig. 2 is the fundamental diagram of the present invention；
Fig. 3 is PC ends voice de-noising algorithm flow chart；
Fig. 4 is PC ends Speech separation algorithm flow chart.
In figure：
10 apparatus for processing audio,
11 microphone arrays, 12 amplifiers, 13 audio decoders；
20 data transmission devices,
21 communication interfaces, 22 controllers, 23 external expansion interfaces, 24 radiofrequency emitting modules,
25 radiating antennas, 26 reception antennas, 27 Receiver Modules；
30 terminal data processing devices,
31 communication interfaces, 32 PC ends；
40 power supplys.
Specific embodiment
Describe in detail with reference to the accompanying drawings and examples：
First, system
1st, overall
Such as Fig. 1, the system include apparatus for processing audio 10, data transmission device 20, terminal data processing device 30 and power supply 40；
Its annexation is：
Apparatus for processing audio 10, data transmission device 20 and terminal data processing device 30 are sequentially connected；
Power supply 40 is connected with apparatus for processing audio 10 and data transmission device 20 respectively.
Its working mechanism is：
Management and control of the apparatus for processing audio 10 by data transmission device 20, are that data transmission device 20 provides basic data money
Material；
Data processing equipment 20 is managed to apparatus for processing audio 10 and controls, and is that terminal data processing device 30 provides and waits to locate
Reason data；
The data of 30 processing data transmitting device of terminal data processing device transmission；
Apparatus for processing audio 10, data link is powered by power supply 40.
Such as Fig. 2, its working-flow is：
Collection birds voice believed signal before this；
Then the transmission of speech data is carried out using radio-frequency module；
Finally data are processed at PC ends, first the voice to gathering utilizes a kind of improved Wiener filtering algorithm noise reduction；Connect
Get off and mixing voice is separated based on the DUET Speech separation algorithms that PDTA is clustered to clean speech using a kind of, obtain source voice
Number is birds quantity survey number.
2nd, functional part
1）Apparatus for processing audio 10
Apparatus for processing audio 10 includes microphone array 11, amplifier 12 and the audio decoder 13 being sequentially connected；
（1）Microphone array 11
Microphone array 11 adopts multiple high-fidelity type mikes；
Birds voice is acquired, is amplified through 12 signal of amplifier in the birds voice that will be collected.
（2）Amplifier 12
Amplifier of the amplifier 12 using model OPA684 of TI companies；
The voice signal for gathering is amplified, the voice transfer for amplifying signal is decoded to audio decoder 13.
（3）Audio decoder 13
Audio processing chip TLV320AIC34 of the audio decoder 13 using the production of TI companies；
Modulation is decoded to audio signal, and the signal of collection is sent to data transmission device 20.
2）Data transmission device
Communication interface 21 that data transmission device 20 includes being sequentially communicated, controller 22, external expansion interface 23, radio-frequency transmissions mould
Block 24, transmitting antenna 25, reception antenna 26, Receiver Module 27.
（1）Communication interface 21
Communication interface 21 is a kind of multi-functional synchronous serial interface, with very strong programmability, is configurable to multiple
Synchronous serial interface standard, directly with various device high-speed interfaces；
Communication between responsible external audio processing meanss 10 and controller 22.
（2）Controller 22
TMS320C6713 of the controller 22 using TI companies（225 MHz of dominant frequency）Type dsp chip；
Mainly it is responsible for being managed apparatus for processing audio 10 and radiofrequency emitting module 24 and controlling.
（3）External expansion interface 23
External expansion interface 23 is a kind of interface provided by controller 22；
It is mainly used in connecting radiofrequency emitting module 24, realizes control and management of the controller 22 to radio communication.
（4）Radiofrequency emitting module 24
Wireless microwave equipment of the radiofrequency irradiation module 24 using the external antenna of model VS-5854, transmission power is 28dBm,
High receiving sensitivity 802.11a/n agreement, in 5.150-5.850GHz, transmission range is up to 30 kilometers for working frequency range.
（5）Transmitting antenna 25
Transmitting antenna 25 adopts MIMO double antenna patterns, V+H polarity, and the gain of antenna is 28Bi, lobe angle：V：40 degree, H：
60 degree.
（6）Reception antenna（26）
Transmitting antenna（26）Using MIMO double antenna patterns, V+H polarity, the gain of antenna is 28Bi, lobe angle：V：40 degree,
H：60 degree.
（7）Receiver Module 27
Receiver Module 27 using model VS-5854 external antenna Wireless microwave equipment, working method be point-to-point,
The mode of point-to-multipoint, frequency range passage adjust automatically, eliminates the trouble of manual modification.
3）Terminal data processing device 30
Terminal data processing device 30 includes front latter linked communication interface 31 and PC ends 32；
The data that collection is processed by PC ends 32, based on MATLAB platform processes mixing voices, reach voice point using respective algorithms
From purpose.
（1）Communication interface 31
Communication interface 31 is a kind of multi-functional synchronous serial interface, with very strong programmability, is configurable to multiple
Synchronous serial interface standard, directly with various device high-speed interfaces；
Communication between responsible Receiver Module 27 and PC ends 32.
（2）PC ends 32
PC ends 32 are computer, and which is embedded with the working software of this method；
The data that sends back are processed by PC ends 32, estimate the number of source voice.
2nd, method
1st, the workflow of voice de-noising
Such as Fig. 3, the workflow of voice de-noising are as follows：
A, system initialization -301；
B, to gather voice pre-removal is carried out to noise using spectrum-subtraction, to improve the signal to noise ratio -302 of input speech signal；
C, the noise power spectrum for calculating front 5 frame signal, used as the initial value -303 of dynamic estimation；
D, carry out end-point detection to Noisy Speech Signal using subband spectrum entropy, and record the starting point of sound section of voice signal with
Terminating point -304；
E, judge whether the frame signal is sound section -305, be then entrance step G, otherwise enter step F；
F, renewal noise power spectrum -306；
G, Wiener filtering noise reduction -307.
2nd, the workflow of speech Separation
Such as Fig. 4, the workflow of speech Separation are as follows：
A, to noise reduction after clean speech carry out adding window and framing pretreatment -401；
B, Fourier's change, carry out rarefaction representation -402 to voice signal；
C, normalization are made on the upper semicircumference of speech data point chorologic unit circle, ask each point to arrive（1,0）Radian, to radian value
Carry out M region division -403；
D, the probability density -404 for calculating each region；
E, density peaks -405 are obtained using local optimum resolving Algorithm；
F, the corresponding radian value of searching peak value, can calculate hybrid matrix A-406；
G, using DUET algorithms, each for mixing voice data point is projected in all directions of hybrid matrix A, according to projector distance
Judge which source voice class is each data point belong to, you can recover each source voice -407.
Claims (6)
1. a kind of bird community quantity survey system, it is characterised in that：
Including apparatus for processing audio（10）, data transmission device（20）, terminal data processing device（30）And power supply（40）；
Apparatus for processing audio（10）, data transmission device（20）With terminal data processing device（30）It is sequentially connected；
Power supply（40）Respectively with apparatus for processing audio（10）And data transmission device（20）Connection.
2. a kind of bird community quantity survey system according to claim 1, it is characterised in that：
Described apparatus for processing audio（10）Including the microphone array being sequentially connected（11）, amplifier（12）And audio decoder
（13）.
3. a kind of bird community quantity survey system according to claim 1, it is characterised in that：
Described data transmission device（20）Including the communication interface being sequentially communicated（21）, controller（22）, external expansion interface
（23）, radiofrequency irradiation module（24）, radiating antenna（25）, reception antenna（26）And Receiver Module（27）.
4. the bird community quantity survey method based on system described in claim 1,2,3, it is characterised in that：
1. voice de-noising
Birds mixing voice Y is gathered in the field environment using microphone array, framing adding window is carried out to the voice for gathering and is located in advance
Manage, extracting the good characteristic parameter spectrum entropy of noise immunity carries out end-point detection, judges there is words frame and without words frame noise, using Wiener filtering
Noise reduction algorithm carries out noise reduction process to the voice for gathering, and obtains pure birds voice；
2. speech Separation
Speech Separation is divided into peak estimation and source voice recovers two stages：
In the peak estimation stage, adding window, framing, Fourier transformation is carried out to clean speech, realize the rarefaction representation to gathering voice,
Pretreatment is carried out to rarefaction speech data again, is allowed on the upper semicircumference of speech data point chorologic unit circle, is asked each point to arrive（1,
0）Radian, region division is carried out to radian value, the probability density in each region is calculated, is obtained using local optimum resolving Algorithm close
Degree peak value, the number of peak value are the number for separating voice；
Source voice Restoration stage, finds the corresponding radian value of peak value, calculates hybrid matrix A, that is, need to solve Y=AX nonhomogeneous equations
Group, using DUET algorithms, is projected in each for mixing voice data point in all directions of hybrid matrix A, is sentenced according to projector distance
Which source voice class is fixed each data point belong to, you can recover each source voice X.
5. the bird community quantity survey method as described in claim 4, it is characterised in that the workflow of voice de-noising is as follows：
A, system initialization（301）；
B, to gather voice pre-removal is carried out to noise using spectrum-subtraction, to improve the signal to noise ratio of input speech signal（302）；
C, the noise power spectrum for calculating front 5 frame signal, used as the initial value of dynamic estimation（303）；
D, carry out end-point detection to Noisy Speech Signal using subband spectrum entropy, and record the starting point of sound section of voice signal with
Terminating point（304）；
E, judge whether the frame signal is sound section（305）, it is then to enter step G, otherwise enters step F；
F, renewal noise power spectrum（306）；
G, Wiener filtering noise reduction（307）.
6. the bird community quantity survey method as described in claim 4, its feature are as follows in the workflow of speech Separation：
A, to noise reduction after clean speech carry out adding window and framing pretreatment（401）；
B, Fourier's change, carry out rarefaction representation to voice signal（402）；
C, normalization are made on the upper semicircumference of speech data point chorologic unit circle, ask each point to arrive（1,0）Radian, to radian value
Carry out M region division（403）；
D, the probability density for calculating each region（404）；
E, density peaks are obtained using local optimum resolving Algorithm（405）；
F, the corresponding radian value of searching peak value, can calculate hybrid matrix A（406）；
G, using DUET algorithms, each for mixing voice data point is projected in all directions of hybrid matrix A, according to projector distance
Judge which source voice class is each data point belong to, you can recover each source voice（407）.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610969673.7A CN106504762B (en) | 2016-11-04 | 2016-11-04 | Bird community number estimation system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610969673.7A CN106504762B (en) | 2016-11-04 | 2016-11-04 | Bird community number estimation system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106504762A true CN106504762A (en) | 2017-03-15 |
| CN106504762B CN106504762B (en) | 2023-04-14 |
Family
ID=58322033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610969673.7A Expired - Fee Related CN106504762B (en) | 2016-11-04 | 2016-11-04 | Bird community number estimation system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106504762B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107369451A (en) * | 2017-07-18 | 2017-11-21 | 北京市计算中心 | A kind of birds sound identification method of the phenology research of auxiliary avian reproduction phase |
| CN109671439A (en) * | 2018-12-19 | 2019-04-23 | 成都大学 | A kind of intelligence fruit-bearing forest bird pest prevention and treatment equipment and its birds localization method |
| CN109741759A (en) * | 2018-12-21 | 2019-05-10 | 南京理工大学 | A kind of acoustics automatic testing method towards specific birds species |
| CN111626093A (en) * | 2020-03-27 | 2020-09-04 | 国网江西省电力有限公司电力科学研究院 | Electric transmission line related bird species identification method based on sound power spectral density |
| CN112992172A (en) * | 2021-01-28 | 2021-06-18 | 广州大学 | Single-channel time domain bird song separating method based on attention mechanism |
| CN113225400A (en) * | 2021-05-08 | 2021-08-06 | 南京林业大学 | Bird population density monitoring system and method based on singing of singing birds |
| CN113439304A (en) * | 2019-02-26 | 2021-09-24 | 哈曼国际工业有限公司 | Voice separation method and system based on degradation separation estimation technology |
| JP7084568B1 (en) | 2021-06-01 | 2022-06-15 | 広東省科学院動物研究所 | Bird attraction monitoring devices and methods for restoring bird diversity in wetland parks |
| CN117809662A (en) * | 2024-02-28 | 2024-04-02 | 江西师范大学 | Method and system for adjusting habitat environment based on bird feature recognition |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005029463A1 (en) * | 2003-09-05 | 2005-03-31 | Kitakyushu Foundation For The Advancement Of Industry, Science And Technology | A method for recovering target speech based on speech segment detection under a stationary noise |
| WO2006049052A1 (en) * | 2004-11-02 | 2006-05-11 | Matsushita Electric Industrial Co., Ltd. | Noise suppresser |
| CN102065272A (en) * | 2009-11-13 | 2011-05-18 | 中国科学院遥感应用研究所 | Acoustic image integrated wild bird recognition technology-based remote wireless monitoring system |
| CN202058443U (en) * | 2011-05-09 | 2011-11-30 | 杨捷 | Bird voice recognition system |
| US20140185415A1 (en) * | 2012-05-22 | 2014-07-03 | Tianjin Changyue Electronic Technology Co. Ltd. | Alarm device for banishment of birds and animals |
| US20140226838A1 (en) * | 2013-02-13 | 2014-08-14 | Analog Devices, Inc. | Signal source separation |
| CN104658538A (en) * | 2013-11-18 | 2015-05-27 | 中国计量学院 | Mobile bird recognition method based on birdsong |
| CN105405441A (en) * | 2015-10-20 | 2016-03-16 | 北京云知声信息技术有限公司 | Method and device for voice information feedback |
-
2016
- 2016-11-04 CN CN201610969673.7A patent/CN106504762B/en not_active Expired - Fee Related
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2005029463A1 (en) * | 2003-09-05 | 2005-03-31 | Kitakyushu Foundation For The Advancement Of Industry, Science And Technology | A method for recovering target speech based on speech segment detection under a stationary noise |
| WO2006049052A1 (en) * | 2004-11-02 | 2006-05-11 | Matsushita Electric Industrial Co., Ltd. | Noise suppresser |
| CN102065272A (en) * | 2009-11-13 | 2011-05-18 | 中国科学院遥感应用研究所 | Acoustic image integrated wild bird recognition technology-based remote wireless monitoring system |
| CN202058443U (en) * | 2011-05-09 | 2011-11-30 | 杨捷 | Bird voice recognition system |
| US20140185415A1 (en) * | 2012-05-22 | 2014-07-03 | Tianjin Changyue Electronic Technology Co. Ltd. | Alarm device for banishment of birds and animals |
| US20140226838A1 (en) * | 2013-02-13 | 2014-08-14 | Analog Devices, Inc. | Signal source separation |
| CN104995679A (en) * | 2013-02-13 | 2015-10-21 | 美国亚德诺半导体公司 | Signal source separation |
| CN104658538A (en) * | 2013-11-18 | 2015-05-27 | 中国计量学院 | Mobile bird recognition method based on birdsong |
| CN105405441A (en) * | 2015-10-20 | 2016-03-16 | 北京云知声信息技术有限公司 | Method and device for voice information feedback |
Non-Patent Citations (2)
| Title |
|---|
| 谭北海;谢胜利;: "基于源信号数目估计的欠定盲分离" * |
| 颜鑫;李应;: "利用抗噪幂归一化倒谱系数的鸟类声音识别" * |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107369451A (en) * | 2017-07-18 | 2017-11-21 | 北京市计算中心 | A kind of birds sound identification method of the phenology research of auxiliary avian reproduction phase |
| CN109671439A (en) * | 2018-12-19 | 2019-04-23 | 成都大学 | A kind of intelligence fruit-bearing forest bird pest prevention and treatment equipment and its birds localization method |
| CN109671439B (en) * | 2018-12-19 | 2024-01-19 | 成都大学 | Intelligent fruit forest bird pest control equipment and bird positioning method thereof |
| CN109741759A (en) * | 2018-12-21 | 2019-05-10 | 南京理工大学 | A kind of acoustics automatic testing method towards specific birds species |
| CN109741759B (en) * | 2018-12-21 | 2020-07-31 | 南京理工大学 | Acoustic automatic detection method for specific bird species |
| CN113439304A (en) * | 2019-02-26 | 2021-09-24 | 哈曼国际工业有限公司 | Voice separation method and system based on degradation separation estimation technology |
| CN111626093A (en) * | 2020-03-27 | 2020-09-04 | 国网江西省电力有限公司电力科学研究院 | Electric transmission line related bird species identification method based on sound power spectral density |
| CN111626093B (en) * | 2020-03-27 | 2023-12-26 | 国网江西省电力有限公司电力科学研究院 | Method for identifying related bird species of power transmission line based on sound power spectral density |
| CN112992172B (en) * | 2021-01-28 | 2023-09-15 | 广州大学 | Single-channel time domain bird song separation method based on attention mechanism |
| CN112992172A (en) * | 2021-01-28 | 2021-06-18 | 广州大学 | Single-channel time domain bird song separating method based on attention mechanism |
| CN113225400A (en) * | 2021-05-08 | 2021-08-06 | 南京林业大学 | Bird population density monitoring system and method based on singing of singing birds |
| JP2022184687A (en) * | 2021-06-01 | 2022-12-13 | 広東省科学院動物研究所 | Bird attracting monitoring device and method for restoring diversity of birds in wetland park |
| JP7084568B1 (en) | 2021-06-01 | 2022-06-15 | 広東省科学院動物研究所 | Bird attraction monitoring devices and methods for restoring bird diversity in wetland parks |
| CN117809662A (en) * | 2024-02-28 | 2024-04-02 | 江西师范大学 | Method and system for adjusting habitat environment based on bird feature recognition |
| CN117809662B (en) * | 2024-02-28 | 2024-05-10 | 江西师范大学 | Method and system for adjusting habitat environment based on bird feature recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106504762B (en) | 2023-04-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106504762A (en) | Bird community quantity survey system and method | |
| CN101505447B (en) | Method of estimating weighting function of audio signals in a hearing aid | |
| CN107862060B (en) | Semantic recognition device and recognition method for tracking target person | |
| CN103948398B (en) | Be applicable to the heart sound location segmentation method of android system | |
| CN109874096A (en) | A kind of ears microphone hearing aid noise reduction algorithm based on intelligent terminal selection output | |
| CN107682240A (en) | A kind of distributed sound interactive system for intelligent domestic | |
| CN112037789A (en) | Equipment awakening method and device, storage medium and electronic device | |
| EP1533964A3 (en) | High data through put wireless local area network reciever | |
| AU2010204470A1 (en) | Automatic sound recognition based on binary time frequency units | |
| CN109473119B (en) | Acoustic target event monitoring method | |
| CN103219012A (en) | Double-microphone noise elimination method and device based on sound source distance | |
| CN110875045A (en) | Voice recognition method, intelligent device and intelligent television | |
| CN107481729A (en) | A kind of method and system that intelligent terminal is upgraded to far field speech-sound intelligent equipment | |
| CN112273366A (en) | Method and system for ecologically repelling birds by agricultural unmanned aerial vehicle in rice direct seeding cultivation | |
| CN106340305A (en) | Self-calibration far-field voice interaction device and far-field voice self-calibration method | |
| CN108122559A (en) | Binaural sound sources localization method based on deep learning in a kind of digital deaf-aid | |
| CN111901737A (en) | Hearing aid parameter self-adaption method based on intelligent terminal | |
| CN107077844A (en) | Method and device for realizing voice combined assistance and robot | |
| CN201585128U (en) | Array microphone hearing-aid based on mobile phone platform | |
| CN206237414U (en) | Voice transmission device, pronunciation receiver and unmanned plane voice broadcast service system | |
| CN107592600A (en) | A kind of pickup screening technique and sound pick up equipment based on distributed microphone | |
| CN114639169A (en) | Human body action recognition system based on attention mechanism feature fusion and position independence | |
| CN102045467B (en) | Audio signal sound production system for eliminating environmental noise | |
| CN102388624B (en) | Sound processing device and sound processing method | |
| EP1811756A3 (en) | Method of processing radio frequency signal in mobile terminal as well as mobile communication system and mobile terminal using the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20230414 |