The use of acoustic contextual information in HMM-Based speech recognition

Abstract

A novel method is proposed to incorporate acoustic contextual information into speech recognition systems based on the hidden Markov model (HMM). Frame correlation exponents and transition costs are introduced to measure the effects of contextual information and modify maximum likelihood solutions in standard HMM's. The contextual information parameters reflect both time correlation among feature vectors and boundary effects between HMM states. Significant reduction of error rates is achieved for a continuous speech recognition task.