EUROSPEECH 2003 - INTERSPEECH 2003
The performance of speaker verification (SV) systems degrades rapidly in noise rendering them unsuitable for security-critical applications in mobile phones, where false acceptance rates (FAR) of ~ 10^-4 are required. However, less demanding applications for which equal error rates (EER) comparable to word error rates (WER) of speech recognizers are acceptable could benefit from the SV technology. In this paper we evaluate two feature-based noise compensation algorithms in the context of SV: vector Taylor series (VTS) combined with statistical linear approximation (SLA), and Kalman filter-based interacting multiple models (IMM). Tests with the YOHO database and the NTT-AT ambient noises show that EERs as low as 5%-10% in medium to high noise conditions can be achieved for a text-independent SV system.
Bibliographic reference. Suhadi, Suhadi / Stan, Sorel / Fingscheidt, Tim / Beaugeant, Christophe (2003): "An evaluation of VTS and IMM for speaker verification in noise", In EUROSPEECH-2003, 1669-1672.