Speaker Verification System using Hybrid Model with Pitch Detection by Adapted Continuous Wavelet Transform

Abstract

In this paper, pitch detection method adapted continuous wavelet transform(ACWT) is considered to improve the performance of hybrid speaker recognitionsystem.We considered two schemes to design ACWT. One is the scheme to search basis library covering the whole band of speech fundamental frequency (speech pitch). The other is the scheme to determine which one is the best basis.Information cost functional is used for the criterion for the latter. ACWT is enough to classify the pitch of speech very well, even through the speech signal is badly damaged by enviromental noises. With the pitch detection method, hybrid speaker verification(SVS) is developed.