ISCA Archive RSR 1997
ISCA Archive RSR 1997

Noise robust HMM-based speech recognition using segmental cepstral feature vector normalization

Olli Viikki, Kari Laurila

To date, speech recognition systems have been applied in real world applications in which they must be able to provide a satisfactory recognition performance under various noise conditions. However, a mismatch between the training and testing conditions often causes a drastic decrease in the performance of the systems. In this paper, we propose a segmental feature vector normalization technique which makes an automatic speech recognition system more robust to environmental changes by normalizing the output of the signal-processing front-end to have similar segmental statistics in all noise conditions. The viability of the suggested technique was verified in various experiments using different background noises and microphones. In an isolated-word recognition task, the proposed normalization technique reduced the error rates over 70% in noisy conditions with respect to the baseline tests, and in a microphone mismatch case, over 75% error rate reduction was achieved.