Robust Speaker Recognition in Cross-Channel Condition

One of the most difficult challenges for speaker recognition is dealing with channel variability. In this paper, several new techniques of cross-channel compensation of speech signal are used for text-independent speaker verification system. These new techniques include wideband noise reduction, echo cancellation, a simplified feature-domain latent factor analysis and data-driven score normalization. The performance of different techniques across varying channel train/test conditions are presented and discussed, finding that speech enhancement, which used to be neglected for telephone speech, is essential for cross-channel tasks, and the channel compensation techniques developed for telephone channel speech also perform effectively. The per microphone performance analysis further shows that speech enhancement can boost the effects of other techniques greatly, especially on channels with larger signal-to-noise ratio (SNR) variance. All results are presented on NIST SRE 2006 and 2008 data, showing a promising performance gain compared to the baseline system.