Title :
Speaker-adaptive HMM-based speech recognition with a stochastic speaker classifier
Author :
Imamura, Akihiro
Author_Institution :
NTT Human Interface Lab., Kanagawa, Japan
Abstract :
A speaker-adaptive speech recognition method using a stochastic speaker classifier is proposed. The stochastic speaker classifier decides which spectral feature subspace is suitable for the input speaker by using integrated speaker Markov models. In the acoustic HMMs (hidden Markov models), the observation emission probabilities, are presented as joint probabilities for speaker individuality obtained from the speaker classifier and feature vectors, from the acoustic preprocessor. Evaluation experiments are performed using a telephone speech database of 50 command words and 10 Japanese digits. Using four integrated 9-state ergodic speaker hidden Markov models estimated from the command words uttered by 116 training speakers, the best word recognition accuracy of 98.1% is achieved for the 10 digits uttered by 116 test speakers. This is an improvement of 2% over the conventional pooled training method
Keywords :
Markov processes; speech recognition; Japanese digits; acoustic HMM; acoustic preprocessor; command words; feature vectors; hidden Markov models; integrated speaker Markov models; observation emission probabilities; speaker individuality; speaker-adaptive speech recognition; spectral feature subspace; stochastic speaker classifier; telephone speech database; training speakers; word recognition accuracy; Acoustic emission; Hidden Markov models; Loudspeakers; Performance evaluation; Spatial databases; Speech analysis; Speech recognition; Stochastic processes; Telephony; Testing;
Conference_Titel :
Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference on
Conference_Location :
Toronto, Ont.
Print_ISBN :
0-7803-0003-3
DOI :
10.1109/ICASSP.1991.150469