Improved maximum model distance approach for HMM-based speech recognition systems

Q. H. HE, S. KWONG, K. F. MAN, K. S. TANG

Research output: Journal PublicationsJournal Article (refereed)peer-review

13 Citations (Scopus)

Abstract

This paper proposes an improved maximum model distance (IMMD) approach for HMM-based speech recognition systems based on our previous work. 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.
Original languageEnglish
Pages (from-to)1749-1758
JournalPattern Recognition
Volume33
Issue number10
DOIs
Publication statusPublished - Oct 2000
Externally publishedYes

Funding

This work is supported in part by the City University of Hong Kong Strategic Grant 7000754, City University of Hong Kong Direct Allocation Grant 7100081 and the National Natural Science Foundation of China Project 69881001.

Fingerprint

Dive into the research topics of 'Improved maximum model distance approach for HMM-based speech recognition systems'. Together they form a unique fingerprint.

Cite this