Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Speaker Verification in Noise Using Temporal Constraints

NÚstor Becerra Yoma (1), Tarciano Facco Pegoraro (2)

(1) Dept. of Electrical Eng./University of Chile, Santiago, Chile
(2) Ericsson do Brasil, Sao Paulo-SP, Brazil

This paper addresses the problem of state duration modeling in combination with spectral subtraction and Rasta filtering to cancel both additive and convolutional noise in a text-dependent speaker verification task. The results presented in this paper suggest that temporal constraints can lead to reductions of 30 and 14% in the error rates at SNR equal to 0 and 6dB, respectively, without noise canceling techniques. However, with noise canceling methods, temporal restrictions give a lower improvement. The results here shown propose that state duration modeling can be useful in those cases when the noise reduction is low.


Full Paper

Bibliographic reference.  Yoma, NÚstor Becerra / Pegoraro, Tarciano Facco (2000): "Speaker verification in noise using temporal constraints", In ICSLP-2000, vol.3, 1021-1024.