Speaker verification in mismatch training and testing conditions
Abstract
This paper presents an exhaustive study about the robustness of several parameterizations, with a new database specially acquired for the purpose of a speaker recognition application. This database includes the following variations: different recording sessions (including telephonic and microphonic recordings), recording rooms, and languages (it has been obtained from a bilingual set of speakers). This study has been performed with covariance matrices in a text independent speaker verification application. It reveals that the combination of several parameterizations can improve the robustness in all the scenarios.
Cite
@article{arxiv.2204.00311,
title = {Speaker verification in mismatch training and testing conditions},
author = {Marcos Faundez-Zanuy and Adam Slupinski},
journal= {arXiv preprint arXiv:2204.00311},
year = {2022}
}
Comments
4 pages, published in 6th international conference on spoken language processing (ICSLP 2000), Vol. II, pp.322-325. ICSLP 2000, ISBN 7-80150-144-4/G.18Beijing (China). October 16-20, 2000. arXiv admin note: substantial text overlap with arXiv:2203.00513