abstract = {Humans exhibit a remarkable ability to reliably classify sound sources in the environment even in presence of high levels of noise. In contrast, most engineering systems suffer a drastic drop in performance when speech signals are corrupted with channel or background distortions. Our brains are equipped with elaborate machinery for speech analysis and feature extraction, which hold great lessons for improving the performance of automatic speech processing systems under adverse conditions. The work presented here explores a biologically-motivated multi-resolution speaker information representation obtained by performing an intricate yet computationally-efficient analysis of the information-rich spectro-temporal attributes of the speech signal. We evaluate the proposed features in a speaker verification task performed on NIST SRE 2010 data. The biomimetic approach yields significant robustness in presence of non-stationary noise and reverberation, offering a new framework for deriving reliable features for speaker recognition and speech processing. {\textcopyright} 2012 Nemala et al.; licensee Springer.},
author = {Nemala, Sridhar Krishna and Zotkin, Dmitry N and Duraiswami, Ramani and Elhilali, Mounya},
doi = {10.1186/1687-4722-2012-22},
issn = {1687-4722},
journal = {EURASIP Journal on Audio, Speech, and Music Processing},
number = {1},
pages = {22},
title = {{Biomimetic multi-resolution analysis for robust speaker recognition}},
url = {http://asmp.eurasipjournals.springeropen.com/articles/10.1186/1687-4722-2012-22 https://asmp-eurasipjournals.springeropen.com/articles/10.1186/1687-4722-2012-22},
volume = {2012},
year = {2012}