5th European Conference on Speech Communication and Technology

Rhodes, Greece
September 22-25, 1997

A Parallel Environment Model (PEM) for Speech Recognition and Adaptation

Mazin Rahim

AT&T Labs - Research, Florham Park, NJ, USA

A speech recognitionsystem for modelingan acoustic mismatch across different environments is presented. The basic philos- ophy is to apply discriminative learning techniques to sepa- rate the recognition process, that is represented by a hidden Markov model (HMM), from the environmental process which is denoted by a limited number of translation vectors. Each segment of speech is assigned to an environment and recogni- tion is performed upon projecting the parameters of the HMM to best characterize the acoustic space of that environment. The proposed system provides an interesting framework for better modeling and adaptation of speech signals with varying acoustic conditions. Experimental findings on connected digits recognition for three different environments are reported.

Full Paper

Bibliographic reference.  Rahim, Mazin (1997): "A parallel environment model (PEM) for speech recognition and adaptation", In EUROSPEECH-1997, 1087-1090.