2001: A Speaker Odyssey - The Speaker Recognition Workshop
June 18-22, 2001
In real speaker verification applications, additive or convolutive noise creates a mismatch between training and recognition environments, degrading performance. Parallel Model Combination (PMC) is used successfully to improve the noise robustness of Hidden Markov Model (HMM) based speech recognisers. This paper presents the results of applying PMC to compensate for additive noise with non-stationary signal-to-noise ratios (SNRs) in HMM-based text-dependent speaker verification. Speech and noise data were obtained from the YOHO and NOISEX-92 databases respectively. Speaker recognition Equal Error Rates (EER) are presented for noise-contaminated speech at different SNRs and different noise sources. For example, average EER for speech in operations room noise at 6dB SNR dropped from approximately 20% un-compensated to less than 5% using PMC. Finally, it is shown that PMC improves verification by an average EER reduction of 18.29% under varying SNRs (50% of the speech segment under 0dB SNR).
Full Paper Presentation
Bibliographic reference. Wong, Lit Ping / Russell, Martin J. (2001): "Speaker verification under additive noise conditions with non-stationary SNR using parallel model combination (PMC)", In ODYSSEY-2001, 95-100.