Improved maximum model distance for HMM training
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Pages (from-to) | 783-785 |
| Journal / Publication | Electronics Letters |
| Volume | 35 |
| Issue number | 10 |
| Publication status | Published - 13 May 1999 |
Link(s)
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.
Citation Format(s)
Improved maximum model distance for HMM training. / He, Q. H.; Kwong, S.; Man, K. F. et al.
In: Electronics Letters, Vol. 35, No. 10, 13.05.1999, p. 783-785.
In: Electronics Letters, Vol. 35, No. 10, 13.05.1999, p. 783-785.
Research output: Journal Publications and Reviews (RGC: 21, 22, 62) › 21_Publication in refereed journal › peer-review
