CN202058443U - Bird voice recognition system - Google Patents
Bird voice recognition system Download PDFInfo
- Publication number
- CN202058443U CN202058443U CN2011201446967U CN201120144696U CN202058443U CN 202058443 U CN202058443 U CN 202058443U CN 2011201446967 U CN2011201446967 U CN 2011201446967U CN 201120144696 U CN201120144696 U CN 201120144696U CN 202058443 U CN202058443 U CN 202058443U
- Authority
- CN
- China
- Prior art keywords
- voice recognition
- birds
- recognition system
- bird
- casing
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The utility model discloses a bird voice recognition system, which comprises a casing, a data preprocessing and voice recognition module, a data acquisition device and a voice recognition result output module. The data preprocessing and voice recognition module is mounted in the casing, the data acquisition device is connected with an input end of the data preprocessing and voice recognition module, and the voice recognition result output module is connected with an output end of the data preprocessing and voice recognition module. Background noise in various degrees and mixed in bird squawk can be effectively eliminated, obtained bird squawk can be matched in patterns according to a classification model of the compressed sensing principle, precision of voice recognition is improved, and the bird voice recognition system is smaller in size and portable, and has functions of bird voice recording and recognition. Additionally, corresponding audio files can be stored to relative storage devices by the aid of a provided USB (universal serial bus) interface.
Description
Technical field
The utility model relates to a kind of birds speech recognition system.
Background technology
The forest land is the important component part that constitutes the earth surface vegetation, and birds are core members of woodland ecosystems.The love birds, the protection environment promotes the harmonious development of man and nature environment, is a fundamental state policy of China.For strengthening the consciousness of love birds, effectively promote popularizing of birds knowledge, we are necessary to work out the automatic recognition system of a cover based on birds voice cry very much.In traditional birds observation, people often are not easy more especially to treasure species near birds; And if consider the normal life habit of not interfering birds, descending observation to be not easy to obtain correct information again more at a distance.The birds speech recognition under a kind of exactly prerequisite that keeps respective range, is the speech recognition technology of research object at the birds cry specially.Its main process is by speech recording apparatus, obtains the cry of certain unknown birds, by the analysis and judgement to such sound, thereby obtains the information correct to this kind birds.So promptly can realize the essential information of birds is obtained, protect the life habit of birds and specific again effectively.
Existing speech recognition technology can roughly be divided into several sections: (1) feature extraction: the acoustic feature of its essential characteristic of abstraction reaction from voice signal; (2) modelling: by the acoustic feature in the known speech samples, utilize the intelligent algorithm of appointment that it is trained, purpose is for unique acoustic model of the pronunciation foundation correspondence of each known class and with its preservation; (3) pattern match (recognizer): in the process of identification, the unknown sample of input is carried out the phase knowledge and magnanimity relatively with the acoustics model, and phase knowledge and magnanimity soprano will export as a result of.Yet existing speech recognition technology is often with artificial research object, and its voice acoustic model is generally the female or whole speech based on the mankind's sound, and is to set up under dead room (noiseless) situation mostly.The performance of considering the birds speech recognition system may be subjected to the interference of many extraneous factors, comprise different birds crys, background noise and transmission channel or the like, if existing technology is directly applied to the birds speech recognition, will cause the decline of system performance so in default of effective elimination noise means and Classification and Identification technology.
The utility model content
The purpose of this utility model is to overcome above-mentioned defective of the prior art, a kind of primary speech signal that is used to gather unknown birds is provided, and the primary speech signal of the birds of being gathered carried out pre-service, identification, eliminate ground unrest and extract the birds acoustic feature, and then itself and known data model carried out pattern match, obtain the birds speech recognition system of the specifying information relevant with these birds.
For achieving the above object, the technical scheme that the utility model provides is as follows: a kind of birds speech recognition system is provided, comprise casing, also comprise the data pre-service, the sound identification module that are installed in the casing, the data collector that is connected with this data pre-service, sound identification module input end, the voice identification result output module that is connected with this data pre-service, sound identification module output terminal.
The beneficial effect of a kind of birds speech recognition system described in the utility model is: by constructing a casing, in casing, be equiped with the data pre-service, sound identification module, this data pre-service, the sound identification module input end is connected with data collector, this data pre-service, the sound identification module output terminal is connected with the voice identification result output module, effectively eliminated the ground unrest in various degree that may mix in the birds cry, and utilize the disaggregated model of compressed sensing theory that the birds cry that obtains is carried out pattern match, improved the degree of accuracy of speech recognition, volume is less, be convenient to carry, possess birds voice recording and recognition function, can utilize the USB interface that provides that corresponding audio files is stored on the relevant memory device in addition.
Below in conjunction with drawings and Examples a kind of birds speech recognition system described in the utility model is described further.
Description of drawings
Fig. 1 is the structural representation of a kind of birds speech recognition system described in the utility model;
Fig. 2 is the structure principle chart of a kind of birds speech recognition system described in the utility model;
Fig. 3 is the control flow block diagram of a kind of birds speech recognition system described in the utility model.
Embodiment
Below the preferred example of a kind of birds speech recognition system described in the utility model, therefore do not limit protection domain of the present utility model.
With reference to Fig. 1, Fig. 2, Fig. 3, a kind of birds speech recognition system is provided, comprise casing 1, also comprise the data pre-service, the sound identification module 2 that are installed in the casing 1, the data collector 3 that is connected with this data pre-service, sound identification module 2 input ends, the voice identification result output module 4 that is connected with this data pre-service, sound identification module 2 output terminals.
Described data pre-service, sound identification module 2 are to be made of central processor CPU, electric power management circuit, mass storage, be used for raw tone is carried out pre-service, eliminate the influence that noise brings, thereby the acoustic feature that makes it to obtain after the aftertreatment more can reflect the essential characteristic of birds cry, and the acoustic feature and the database sample of the signal that obtains mated, and make identification and judge.
Described data collector 3 is microphones, and this microphone is installed on the casing 1, is used for obtaining the primary speech signal of extraneous birds.
Described voice identification result output module 4 is to be made of the USB interface, loudspeaker, the LCD display that are installed on the casing 1, and the recognition result (birds information) that is used for obtaining outputs to user side according to specified format and form and preserves.
The Candes professor that described compressed sensing theory is a Stanford University proposed in 2006 and is extensively promoted, its basic thought is one and gathers original signal through behind the linear projection of non-self-adapting, can found original signal by reconstructed according to corresponding restructing algorithm.The advantage of compression sensing is that the data for projection amount of signal is far smaller than the required data volume of traditional sampling method, makes the collection of high-resolution signal no longer rely on traditional Shannon's sampling theorem like this, makes rarefaction representation become possibility.Carry out at the applied compression sensor model being without loss of generality in the middle of the process of birds speech recognition, suppose that below the birds acoustic feature of collecting is vector
We utilize the central data of known birds cry database as measuring matrix so
(wherein m is the signal dimension, and n is known sample size), the compressed sensing theory has provided as y and Φ and has satisfied under the certain condition so, can be by measured value y by finding the solution the optimum l of vector
0Norm (number of nonzero element in the vector) is constructed a sparse signal s, that is:
S.t.y=Φ s.Next again by analyzing the energy distribution of this sparse signal s in every class tweedle sample, we can get that class sample of ceiling capacity as recognition result.
The foregoing description is the utility model preferred implementation; but embodiment of the present utility model is not restricted to the described embodiments; other any do not deviate from change, the modification done under spirit of the present utility model and the principle, substitutes, combination, simplify; all should be the substitute mode of equivalence, be included within the protection domain of the present utility model.
Claims (4)
1. birds speech recognition system, comprise casing (1), it is characterized in that, also comprise the data pre-service, the sound identification module (2) that are installed in the casing (1), the data collector (3) that is connected with this data pre-service, sound identification module (2) input end, the voice identification result output module (4) that is connected with this data pre-service, sound identification module (2) output terminal.
2. a kind of birds speech recognition system according to claim 1 is characterized in that, described data pre-service, sound identification module (2) are to be made of central processor CPU, electric power management circuit, mass storage.
3. a kind of birds speech recognition system according to claim 1 is characterized in that, described data collector (3) is microphone (9), and this microphone (9) is installed on the casing (1).
4. a kind of birds speech recognition system according to claim 1 is characterized in that, described voice identification result output module (4) is to be made of the USB interface (6), loudspeaker (7), the LCD display (8) that are installed on the casing (1).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011201446967U CN202058443U (en) | 2011-05-09 | 2011-05-09 | Bird voice recognition system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011201446967U CN202058443U (en) | 2011-05-09 | 2011-05-09 | Bird voice recognition system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN202058443U true CN202058443U (en) | 2011-11-30 |
Family
ID=45018412
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011201446967U Expired - Fee Related CN202058443U (en) | 2011-05-09 | 2011-05-09 | Bird voice recognition system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN202058443U (en) |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103489446A (en) * | 2013-10-10 | 2014-01-01 | 福州大学 | Twitter identification method based on self-adaption energy detection under complex environment |
CN104658538A (en) * | 2013-11-18 | 2015-05-27 | 中国计量学院 | Mobile bird recognition method based on birdsong |
CN105913840A (en) * | 2016-06-20 | 2016-08-31 | 西可通信技术设备(河源)有限公司 | Speech recognition device and mobile terminal |
CN106328152A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技(杭州)有限公司 | Automatic identification and monitoring system for indoor noise pollution |
CN106504762A (en) * | 2016-11-04 | 2017-03-15 | 中南民族大学 | Bird community quantity survey system and method |
CN109117732A (en) * | 2018-07-16 | 2019-01-01 | 国网江西省电力有限公司电力科学研究院 | A kind of transmission line of electricity relates to the identification of bird failure bird kind figure sound and control method |
CN112800837A (en) * | 2020-12-25 | 2021-05-14 | 广东电网有限责任公司中山供电局 | Bird recognition system and method |
-
2011
- 2011-05-09 CN CN2011201446967U patent/CN202058443U/en not_active Expired - Fee Related
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103489446A (en) * | 2013-10-10 | 2014-01-01 | 福州大学 | Twitter identification method based on self-adaption energy detection under complex environment |
CN103489446B (en) * | 2013-10-10 | 2016-01-06 | 福州大学 | Based on the twitter identification method that adaptive energy detects under complex environment |
CN104658538A (en) * | 2013-11-18 | 2015-05-27 | 中国计量学院 | Mobile bird recognition method based on birdsong |
CN106328152A (en) * | 2015-06-30 | 2017-01-11 | 芋头科技(杭州)有限公司 | Automatic identification and monitoring system for indoor noise pollution |
CN106328152B (en) * | 2015-06-30 | 2020-01-31 | 芋头科技(杭州)有限公司 | automatic indoor noise pollution identification and monitoring system |
CN105913840A (en) * | 2016-06-20 | 2016-08-31 | 西可通信技术设备(河源)有限公司 | Speech recognition device and mobile terminal |
CN106504762A (en) * | 2016-11-04 | 2017-03-15 | 中南民族大学 | Bird community quantity survey system and method |
CN109117732A (en) * | 2018-07-16 | 2019-01-01 | 国网江西省电力有限公司电力科学研究院 | A kind of transmission line of electricity relates to the identification of bird failure bird kind figure sound and control method |
CN112800837A (en) * | 2020-12-25 | 2021-05-14 | 广东电网有限责任公司中山供电局 | Bird recognition system and method |
CN112800837B (en) * | 2020-12-25 | 2023-01-24 | 广东电网有限责任公司中山供电局 | Bird recognition system and method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN202058443U (en) | Bird voice recognition system | |
CN103280220B (en) | A kind of real-time recognition method for baby cry | |
CN101539599B (en) | Digital lightning detection method and device thereof | |
CN112802484B (en) | Panda sound event detection method and system under mixed audio frequency | |
CN106328152B (en) | automatic indoor noise pollution identification and monitoring system | |
CN112735473B (en) | Method and system for identifying unmanned aerial vehicle based on voice | |
CN105919591A (en) | Surface myoelectrical signal based sign language recognition vocal system and method | |
CN110031083A (en) | A kind of noise overall sound pressure level measurement method, system and computer readable storage medium | |
CN207423245U (en) | A kind of Agricultural Environmental Monitoring equipment based on Internet of Things | |
CN208872879U (en) | A kind of microseism data collection system | |
CN104123930A (en) | Guttural identification method and device | |
Oletic et al. | System-level power consumption analysis of the wearable asthmatic wheeze quantification | |
CN103544945B (en) | Portable piezo-ceramic instrument tone recognition system | |
CN105157815A (en) | MEMS sensor for multidirectional high-speed rail noise test and method of MEMS sensor | |
CN109308900A (en) | Headphone device, speech processing system and method for speech processing | |
CN201378190Y (en) | Digital thunder and lightning detection device | |
CN207096984U (en) | A kind of chemical illumination immunity analysis instrument inspection data inquiry unit | |
CN206523222U (en) | A kind of device of environment noise monitoring | |
CN204964008U (en) | A MEMS microphone that is used for multi -direction test high -speed railway noise | |
CN204945699U (en) | A kind of intelligent sound with infrared induction identification | |
CN201780162U (en) | Multichannel noise signal acquisition device | |
CN103759807B (en) | A kind of airport noise monitoring device based on Internet of Things framework | |
CN206313861U (en) | A kind of audio detection system based on the control of NI boards serial ports | |
CN202584719U (en) | Wireless audio acquisition card | |
Tatlas et al. | On the effect of compression on the complexity characteristics of wireless acoustic sensor network signals |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20111130 Termination date: 20120509 |