Speaker verification in noise using a stochastic version of the weighted Viterbi algorithm

Author

Yoma, Nestor Becerra ; Villar, Miguel

Author_Institution

Dept. of Electr. Eng., Chile Univ., Santiago, Chile

Volume

10

Issue

3

fYear

2002

fDate

3/1/2002 12:00:00 AM

Firstpage

158

Lastpage

166

Abstract

This paper proposes the replacement of the ordinary output probability with its expected value if the addition of noise is modeled as a stochastic process, which in turn is merged with the hidden Markov model (HMM) in the Viterbi algorithm. This new output probability is analytically derived for the generic case of a mixture of Gaussians and can be seen as the definition of a stochastic version of the weighted Viterbi algorithm. Moreover, an analytical expression to estimate the uncertainty in noise canceling is also presented. The method is applied in combination with spectral subtraction to improve the robustness to additive noise of a text-dependent speaker verification system. Reductions as high as 30% or 40% in the error rates and improvements of 50% in the stability of the decision thresholds are reported

Keywords

hidden Markov models; noise; probability; speaker recognition; stochastic processes; Gaussians mixture; HMM; additive noise; decision threshold stability; error rate reduction; hidden Markov model; noise cancellation; output probability; stochastic process; stochastic weighted Viterbi algorithm; text-dependent speaker verification system; Additive noise; Algorithm design and analysis; Gaussian processes; Hidden Markov models; Noise cancellation; Noise robustness; Stochastic processes; Stochastic resonance; Uncertainty; Viterbi algorithm;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/TSA.2002.1001980

Filename

1001980