A Framework for Bioacoustic Vocalization Analysis Using Hidden Markov Models

Yao Ren, Michael Johnson, Patrick Clemins, Michael Darre, Sharon Stuart Glaeser, Tomasz Osiejuk, Ebenezer Out-Nyarko
2009 Algorithms  
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
more » ... tures 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 OPEN ACCESS Algorithms 2009, 2 1411 tasks and illustrate the flexibility of the HMM framework for a variety of species, vocalization types, and analysis tasks.
doi:10.3390/a2041410 fatcat:wgwsuk55tnhc5eph4u2ulawozi