DMCA
Feature Warping for Robust Speaker Verification (2001)
| Venue: | ISCA ARCHIVE |
| Citations: | 190 - 10 self |
BibTeX
@MISC{Pelecanos01featurewarping,
author = {Jason Pelecanos and Sridha Sridharan},
title = { Feature Warping for Robust Speaker Verification},
year = {2001}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
We propose a novel feature mapping approach that is robust to channel mismatch, additive noise and to some extent, nonlinear effects attributed to handset transducers. These adverse effects can distort the short-term distribution of the speech features. Some methods have addressed this issue by conditioning the variance of the distribution, but not to the extent of conforming the speech statistics to a target distribution. The proposed target mapping method warps the distribution of a cepstral feature stream to a standardised distribution over a specified time interval. We evaluate a number of the enhancement methods for speaker verification, and compare them against a Gaussian target mapping implementation. Results indicate improvements of the warping technique over a number of methods such as Cepstral Mean Subtraction (CMS), modulation spectrum processing, and short-term windowed CMS and variance normalisation. This technique is a suitable feature post-processing method that may be combined with other techniques to enhance speaker recognition robustness under adverse conditions.
Keyphrases
robust speaker verification adverse condition speech feature target distribution short-term distribution cepstral feature stream nonlinear effect cepstral mean subtraction speaker verification speech statistic suitable feature post-processing method short-term windowed cm variance normalisation warping technique modulation spectrum processing novel feature speaker recognition robustness result indicate improvement gaussian target enhancement method additive noise adverse effect standardised distribution specified time interval
