EUROSPEECH 2001 Scandinavia
7th European Conference on Speech Communication and Technology

Aalborg, Denmark
September 3-7, 2001


Additive and Convolutional Noise Canceling in Speaker Verification Using a Stochastic Weighted Viterbi Algorithm

Nestor Becerra Yoma, Miguel Villar Fernandez

University of Chile, Chile

This paper replaces 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 HMM in the Viterbi algorithm. The method, which can be seen as a weighted matching algorithm, is applied in combination with spectral subtraction and RASTA to improve the robustness to additive and convolutional noise of a text-dependent speaker verification system. Reductions around 10% or 20% in the error rates and improvements as high as 30% or 50% in the stability of the decision thresholds are reported when the ordinary Viterbi algorithm is replaced with the weighted one. When compared with the baseline system, reductions of 70% or 80% are shown.

Full Paper

Bibliographic reference.  Yoma, Nestor Becerra / Fernandez, Miguel Villar (2001): "Additive and convolutional noise canceling in speaker verification using a stochastic weighted viterbi algorithm", In EUROSPEECH-2001, 2845-2848.