Title :
Improved maximum model distance for HMM training
Author :
He, Q.-H. ; Kwong, S. ; Man, K.F. ; Tang, K.S.
Author_Institution :
South China Univ. of Technol., Guangzhou, China
fDate :
5/13/1999 12:00:00 AM
Abstract :
A new approach based on the maximum model distance (IMMD) approach for HMM speech recognition systems is proposed. It defines a more realistic model distance definition for HMM training, and utilises the limited training data in a more effective manner. Theoretical and practical issues concerning this approach are investigated. Experimental results showed that a significant reduction in errors could be achieved with this new approach when compared with the maximum model distance (MMD) criterion
Keywords :
hidden Markov models; speech recognition; HMM training; maximum model distance; speech recognition systems; training data;
Journal_Title :
Electronics Letters
DOI :
10.1049/el:19990550
