Artículo de revista
Telephone Channel Compensation in Speaker Verification Using a Polynomial Approximation in the Log-Filter-Bank Energy Domain
Fecha
2012-01Registro en:
IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING Volume: 20 Issue: 1 Pages: 336-341 Published: JAN 2012
DOI: 10.1109/TASL.2011.2157495
Autor
Garretón, Claudio
Becerra Yoma, Néstor
Institución
Resumen
This correspondence presents a novel feature-space channel compensation technique that models the convolutional distortion in the log-energy mel-filter domain by means of a polynomial approximation. The proposed parametric distortion model generates appropriate constraints in the spectral domain that help to improve the channel cancelling estimation with limited data. In a text-dependent speaker verification task, the polynomial-based channel estimation scheme can lead to reductions in equal error rate (EER) as great as 22% and 8% when compared with the baseline system and with the standard cepstral bias removal approach, respectively, with no significant increase in computational load.