In a speaker-independent, large-vocabulary continuous speech recognition systems, recognition accuracy varies considerably from speaker to speaker, and performance may be significantly degraded for outlier speakers such as nonnative talkers. In this paper, we explore supervised speaker adaptation and normalization in the MLP component of a hybrid hidden Markov model/ multilayer perception version of SRI's DECIPHER(TM) speech recognition system. Normalization is implemented through an additional transformation network that pre-processes the cepstral input to the MLP. Adaptation is accomplished through incremental retraining of the MLP weights on adaptation data. Our approach combines both adaptation and normalization in a single, consistent manner, works with limited adaptation data, and is text-independent. We show significant improvement in recognition accuracy.
Bibliographic reference. Abrash, Victor / Franco, Horacio / Sankar, Ananth / Cohen, Michael (1995): "Connectionist speaker normalization and adaptation", In EUROSPEECH-1995, 2183-2186.