Next Article in Journal
Linear-Time Text Compression by Longest-First Substitution
Previous Article in Journal
Methodology, Algorithms, and Emerging Tool for Automated Design of Intelligent Integrated Multi-Sensor Systems
Previous Article in Special Issue
Classification of Sperm Whale Clicks (Physeter Macrocephalus) with Gaussian-Kernel-Based Networks
Algorithms 2009, 2(4), 1410-1428; doi:10.3390/a2041410

A Framework for Bioacoustic Vocalization Analysis Using Hidden Markov Models

1,* , 2
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 Poznań, Poland
* Author to whom correspondence should be addressed.
Received: 1 September 2009 / Revised: 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)
View Full-Text   |   Download PDF [239 KB, uploaded 19 November 2009]   |   Browse Figures


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) Hidden Markov Model (HMM); Greenwood Frequency Cepstral Coefficients (GFCCs)
This is an open access article distributed under the Creative Commons Attribution License (CC BY 3.0).

Share & Cite This Article

Further Mendeley | CiteULike
Export to BibTeX |
EndNote |
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.

View more citation formats

Related Articles

Article Metrics

For more information on the journal, click here


[Return to top]
Algorithms EISSN 1999-4893 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert