An improved maximum model distance approach for HMM-based speech recognition systems

摘要

This paper proposes an improved maximum model distance (IMMD) approach for HMM-based speech recognition systems based on our previous work [S. Kwong, Q.H. He, K.F. Man, K.S. Tang. A maximum model distance approach for HMM-based speech recognition, Pattern Recognition 31 (3) (1998) 219–229]. It defines a more realistic model distance definition for HMM training, and utilizes the limited training data in a more effective manner. Discriminative information contained in the training data was used to improve the performance of the recognizer. HMM parameter adjustment rules were induced in details. Theoretical and practical issues concerning this approach are also discussed and investigated in this paper. Both isolated word and continuous speech recognition experiments showed that a significant error reduction could be achieved by IMMD when compared with the maximum model distance (MMD) criterion and other training methods using the minimum classification error (MCE) and the maximum mutual information (MMI) approaches.