Algorithms 2009, 2(4), 1410-1428; doi:10.3390/a2041410

A Framework for Bioacoustic Vocalization Analysis Using Hidden Markov Models

1 Electrical and Computer Engineering, Marquette University, Milwaukee, WI 53201, USA 2 American Association for the Advancement of Science, Washington, DC 20005, USA 3 Animal Sciences, University of Connecticut, Storrs, CT 06269, USA 4 Oregon Zoo, Portland, OR 97221, USA 5 Department of Behavioural Ecology, Institute of Environmental Biology, Faculty of Biology, Adam Mickiewicz University, Umultowska 89, 61-614 PoznaƄ, Poland
* Author to whom correspondence should be addressed.
Received: 1 September 2009; in revised form: 30 October 2009 / Accepted: 9 November 2009 / Published: 18 November 2009
(This article belongs to the Special Issue Algorithms for Sound Localization and Sound Classification)
PDF Full-text Download PDF Full-Text [239 KB, uploaded 19 November 2009 14:44 CET]
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 time alignment, the ability to incorporate complex language or recognition constraints, and easy extendibility to continuous recognition and detection domains. In this work, we apply HMMs to several different species and bioacoustic tasks using generalized spectral features that can be easily adjusted across species and HMM network topologies suited to each task. This experimental work includes a simple call type classification task using one HMM per vocalization for repertoire analysis of Asian elephants, a language-constrained song recognition task using syllable models as base units for ortolan bunting vocalizations, and a stress stimulus differentiation task in poultry vocalizations using a non-sequential model via a one-state HMM with Gaussian mixtures. Results show strong performance across all tasks and illustrate the flexibility of the HMM framework for a variety of species, vocalization types, and analysis tasks.
Keywords: Hidden Markov Model (HMM); Greenwood Frequency Cepstral Coefficients (GFCCs)

Article Statistics

Load and display the download statistics.

Citations to this Article

Cite This Article

MDPI and ACS Style

Ren, Y.; Johnson, M.T.; Clemins, P.J.; Darre, M.; Glaeser, S.S.; Osiejuk, T.S.; Out-Nyarko, E. A Framework for Bioacoustic Vocalization Analysis Using Hidden Markov Models. Algorithms 2009, 2, 1410-1428.

AMA Style

Ren Y, Johnson MT, Clemins PJ, Darre M, Glaeser SS, Osiejuk TS, Out-Nyarko E. A Framework for Bioacoustic Vocalization Analysis Using Hidden Markov Models. Algorithms. 2009; 2(4):1410-1428.

Chicago/Turabian Style

Ren, Yao; Johnson, Michael T.; Clemins, Patrick J.; Darre, Michael; Glaeser, Sharon Stuart; Osiejuk, Tomasz S.; Out-Nyarko, Ebenezer. 2009. "A Framework for Bioacoustic Vocalization Analysis Using Hidden Markov Models." Algorithms 2, no. 4: 1410-1428.

Algorithms EISSN 1999-4893 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert