Improved multiple birdsong tracking with distribution derivative method and Markov renewal process clustering
Sound
2014-07-14 v2
Abstract
Segregating an audio mixture containing multiple simultaneous bird sounds is a challenging task. However, birdsong often contains rapid pitch modulations, and these modulations carry information which may be of use in automatic recognition. In this paper we demonstrate that an improved spectrogram representation, based on the distribution derivative method, leads to improved performance of a segregation algorithm which uses a Markov renewal process model to track vocalisation patterns consisting of singing and silences.
Keywords
Cite
@article{arxiv.1302.3462,
title = {Improved multiple birdsong tracking with distribution derivative method and Markov renewal process clustering},
author = {Dan Stowell and Sašo Muševič and Jordi Bonada and Mark D. Plumbley},
journal= {arXiv preprint arXiv:1302.3462},
year = {2014}
}
Comments
Submitted to ICASSP 2013