Improved maximum model distance for HMM training

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

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

2 Citations (Scopus)

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 utilizes 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.
Original languageEnglish
Pages (from-to)783-785
JournalElectronics Letters
Volume35
Issue number10
DOIs
Publication statusPublished - 13 May 1999
Externally publishedYes

Fingerprint

Dive into the research topics of 'Improved maximum model distance for HMM training'. Together they form a unique fingerprint.

Cite this