Feature normalization for speaker verification in room reverberation

• Published in: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 4836 - 4839
• Main Authors: Ganapathy, Sriram, Pelecanos, Jason, Omar, Mohamed Kamal
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2011
• Subjects: Discrete cosine transforms; Feature extraction; Frequency Domain Linear Prediction (FDLP); Mel frequency cepstral coefficient; Reverberation; Room Reverberation; Speaker Verification; Speech; Training
• ISBN: 9781457705380; 1457705389
• ISSN: 1520-6149; 2379-190X
• DOI: 10.1109/ICASSP.2011.5947438

The performance of a typical speaker verification system degrades significantly in reverberant environments. This degradation is partly due to the conventional feature extraction/compensation techniques that use analysis windows which are much shorter than typical room impulse responses. In this paper, we present a feature extraction technique which estimates long-term envelopes of speech in narrow sub-bands using frequency domain linear prediction (FDLP). When speech is corrupted by reverberation, the long-term sub-band envelopes are convolved in time with those of the room impulse response function. In a first order approximation, gain normalization of these envelopes in the FDLP model suppresses the room reverberation artifacts. Experiments are performed on the 8 core conditions of the NIST 2008 speaker recognition evaluation (SRE). In these experiments, the FDLP features provide significant improvements on the interview microphone conditions (relative improvements of 20 30%) over the corresponding baseline system with MFCC features.