Improved maximum model distance for HMM training
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Related Research Unit(s)
|Journal / Publication||Electronics Letters|
|Publication status||Published - 13 May 1999|
|Link to Scopus||https://www.scopus.com/record/display.uri?eid=2-s2.0-0032660823&origin=recordpage|
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.