a framework for bioacoustic vocalization analysis using hidden markov models框架bioacoustic发声使用隐马尔科夫模型分析.pdfVIP

Algorithms 2009, 2, 1410-1428; doi:10.3390/a2041410 OPEN ACCESS algorithms ISSN 1999-4893 /journal/algorithms Article A Framework for Bioacoustic Vocalization Analysis Using Hidden Markov Models Yao Ren 1, Michael T. Johnson 1,*, Patrick J. Clemins 2, Michael Darre 3, 4 5 3 Sharon Stuart Glaeser , Tomasz S. Osiejuk and Ebenezer Out-Nyarko 1 Electrical and Computer Engineering, Marquette University, Milwaukee, WI 53201, USA; E-Mail: yao.ren@ (Y.R.) 2 American Association for the Advancement of Science, Washington, DC 20005, USA; E-Mail: patrick@ (P.C.) 3 Animal Sciences, University of Connecticut, Storrs, CT 06269, USA; E-Mails: Michael.darre@ (M.D.); ebenezer.otu-nyarko@ (E.O.-N.) 4 Oregon Zoo, Portland, OR 97221, USA; E-Mail: sharon@ (S.S.G.) 5 Department of Behavioural Ecology, Institute of Environmental Biology, Faculty of Biology, Adam Mickiewicz University, Umultowska 89, 61-614 Poznań, Poland; E-Mail: osiejuk@.pl (T.S.O.) * Author to whom correspondence should be addressed; E-Mail: mike.johnson@; Tel.: +414-288-0631; Fax: +414-288-5579. Received: 1 September 2009; in revised form: 30 October 2009 / Accepted: 9 November 2009 / Published: 18 November 2009 Abstract: Using Hidden Markov Models (HMMs) as a recognition framework for automatic classification of animal vocalizations has a number of benefits, including the ability to handle duration variability through nonlinear ti