Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Transactions of the Chinese Society of Agricultural Engineering》 2015-24
Add to Favorite Get Latest Update

Vocal signal recognition of ewes based on power spectrum and formant analysis method

Xuan Chuanzhong;Wu Pei;Ma Yanhua;Zhang Li′na;Han Ding;Liu Yanqiu;College of Mechanical and Electrical Engineering, Inner Mongolia Agricultural University;  
Inner Mongolia and its surrounding areas in the west are developing an intensive and large-scale sheep farming operation, in which sheep are bred with planting forage and are placed in captive facilities. However, the breeding pattern of such operation needs a high level of animal welfare management. Considering that sheep makes different vocalization in different emergent situations, ewes' vocalization can be used as an important evidence for ewes' health monitoring and breeding welfare evaluation. In this paper, taking Small Tail Han sheep as an example, ewes' vocalization signals were evenly collected from 80 adult ewes under 3 stress behaviors including searching lamb, hunger, and scare via a wireless audio surveillance device. Then, these continuous vocal signals of ewes were split into 1 200 single call signals using Audacity Acoustic Edit software. The band-pass filter and wavelet denoising methods were applied to preprocess those single sound signals. Six hundred of those sound signals, which were comprised of three different stress behaviors by random selected 200 signals, were analyzed to extract ewes' acoustic characteristic parameters using auto-regressive(AR) power spectrum estimation and formant extraction methods, respectively. Therefore, six representative frequency characteristic parameters from AR power spectrum estimation method were extracted: the power spectrum density mean, the geometric mean, the median value, the trimmed mean, the mean absolute deviation, and inter quartile deviation, and characteristics parameters from formant analysis method were the first, second and third formant frequency. Moreover, typical time-domain characteristic parameters such as signal maximum value, duration value and interval value were taken as well. Then, these characteristic parameters were used to train the back propagation(BP) neural network model of ewes' vocalization recognition, and the rest of 600 vocal signals were used to test the effects of the recognition mode. The results demonstrated that characteristic parameters of ewes' vocal signals were obviously different under different stress behaviors. Furthermore, if BP recognition network was trained by formant parameters, the average correct recognition rate of ewes' vocal signal was 85.3%, higher than AR power spectrum estimation parameters of 81.0%. When BP network was trained by a combination of above two kinds of characteristic parameters, the average correct recognition rate was 93.8%, which meant that the performance of the combination parameters was better than another two methods. However, the average false positive rate still reached 6.2% because ewes' vocal signals under the same stress behavior had a certain degree of difference due to the different age and weight as well as sound volume strength. The results of this study also indicated that analysis of vocalization could be an indicator of different physiological conditions in sheep and may be an important role for understanding communications in ewes.
【Fund】: 国家科技支撑项目(2014BAD08B05);; 国家自然科学基金项目(11364029);; 内蒙古自然科学基金项目(2012MS0720);; 内蒙古“草原英才”产业创新人才团队项目(内组通字[2014]27号);; 内蒙古农业大学科技创新团队项目(NDTD2013-6)
【CateGory Index】: S826
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
【Citations】
Chinese Journal Full-text Database 2 Hits
1 GUO Min1,WU Xiao-Min2,REN Jian-She3,ZHANG Jun-Feng3,LI Ya-Wei1,WANG An-Wen1,DING Chang-Qing4,5**1.College of Computer Science,Shaanxi Normal University,Xi'an 710062,China2.Shaanxi Institute of Zoology,Xi'an 710032,China3.Shaanxi Rare Wild Animals Rescuing and Breeding Research Center,Zhouzhi,Shaanxi 710402,China4.Institute of Zoology,Chinese Academy of Sciences,Beijing 100101,China5.College of Biological Sciences and Biotechnology,Beijing Forestry University, Beijing 100083,China;Vocal characteristics of the crested ibis Nipponia nippon during the breeding season[J];Acta Zoologica Sinica;2007-05
2 WANG En-ze;HE Dong-jian;College of Mechanical and Electronic Engineering,Northwest A&F University;;Bird recognition based on MFCC and dual-GMM[J];Computer Engineering and Design;2014-05
【Co-citations】
Chinese Journal Full-text Database 1 Hits
1 QU Wen-Hui,LI Feng *,SHA Jian-Bin,ZHANG Yu-Ming(College of Wildlife Resources,Northeast Forestry University,Harbin 150040,China);Analyzing Japanese marsh warbler(Megalurus pryeri) song behavior in the breeding season[J];Zoological Research;2011-02
【Secondary Citations】
Chinese Journal Full-text Database 10 Hits
1 ;RECOVERY OF JAPANESE CRESTED IBIS IN QIN-LING RANGE[J];Acta Zoologica Sinica;1981-03
2 (WU YI) (Sichuan Normal College,Nanchong,637002 Sichuan) (PENG JI-TAI GAO HONG) (Ganzi Forest Office, Ganzi, Sichuan,626000) (ZHANG HE-MING) (Wolong Giant Panda Research Center,Wenchuan ,Sichuan,623006);SONAGRAM STRUCTURE OF CALLS IN TIBETAN EARED PHEASANT(CROSSOPTILON CROSSOPTILON)[J];Acta Zoologica Sinica;1995-02
3 JIANG SHI-REN; DING PING ;ZHUGE YANG; WU YAN-CHUN (Department of Biological Science and Biotechnology, Hangzhou University, Hangzhou 310012);CHARACTERISTICS OF SONGS OF THE CHINESE BULBUL (Pycnonotus sinensis) IN THE BREEDING SEASON[J];Acta Zoologica Sinica;1996-03
4 LEI Fu Min ** , WANG Ai Zhen, WANG Gang, YIN Zuo Hua Institute of Zoology, The Chinese Academy of Sciences, Beijing 100080, China;Complexity of calls and songs in the white-rumped snow finch Onychostruthus taczanowskii[J];Acta Zoologica Sinica;2004-03
5 ZHANG Peng 1,2, LI Bao-Guo 1**, WATANABE Kunio21. College of Life Sciences, Northwest University, Xi’an 710069, China2. Primate Research Institute, Kyoto University, Inuyama 484-8506,Japan;Use of forest strata by Sichuan snub-nosed monkeys Rhinopithecus roxellana in spring and winter in Qinling Mountains, China[J];Acta Zoologica Sinica;2006-03
6 LIU Ru Sun\ YU Qing\ DING Wen Ning (Institute of Zoology,The Chinese Academy of Sciences,\ Beijing\ 100080,China) ZHAO Xin Ru (Beijing Normal University,Beijing 1000875,China);THE VOCAL BEHAVIOR OF GARRULAX ELLIOTII[J];ACTA ZOOLOGICA SINICA;1997-S1
7 DING Chang-Qing~① LI Feng~(①②)(① Institute of Zoology,Chinese Academy of Sciences,Beijing 100080;② Graduate School of Chinese Academy of Sciences,Beijing 100049,China);Conservation and Research of Crested Ibis[J];Chinese Journal of Zoology;2005-06
8 LEI Fu-Min WANG Gang(Institute of Zoology, Chinese Academy of Sciences, Beijing 100080);AN APPROACH TO DIFFERENTIATION AND SPECIATION OF BIRDS BASED ON VOCALIZATION[J];Acta Zootaxonomica Sinica;2002-03
9 Li Peixun Yu Xuefeng (Biology Department of Harbin Normal University) Li Fangman (Biology Department of Mudanjiang Teachers' Collage);INTRASPECIFIC INDIVIDUAL RECOGNITION BY SONG IN YELLOW-THROATED BUNTINGDURING BREEDING SEASON[J];Zoological Research;1991-02
10 Jiang Shiren; Ding Ping; Zhuge Yang (Department of Biological Scicnce and Biotechnology, Hangzhou University, Hangzhou 310012 P. R. China);THE COMPARATIVE STUDIES ON THE CHARACTERISTICS OF CHINESE BULBUL SONGS BETWEEN SHENSI ISLAND AND HANGZHOU AREA[J];ZOOLOGICAL RESEARCH;1994-03
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved