|
Researchspace >
General science, engineering & technology >
General science, engineering & technology >
General science, engineering & technology >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/10204/5512
|
| Title: | Appropriate baseline values for HMM-based speech recognition |
| Authors: | Barnard, E
Gouws, E
Wolvaardt, K
Kleynhans, N |
| Keywords: | Hidden markov models
Pronunciation dictionaries
Human language technologies
Speech recognition
PRASA 2004
Pattern recognition |
| Issue Date: | Nov-2004 |
| Publisher: | PRASA 2004 |
| Citation: | Barnard, E, Gouws, E, Wolvaardt, K and Kleynhans, N. 2004. Appropriate baseline values for HMM-based speech recognition. 15th Annual Symposium of the Pattern Recognition Association of South Africa, Grabouw, South Africa, 25 to 26 November 2004 |
| Abstract: | A number of issues realted to the development of speech-recognition systems with Hidden Markov Models (HMM) are discussed. A set of systematic experiments using the HTK toolkit and the TMIT database are used to elucidate matters such as the number of mixtures to use for a particular training-set size, the utility of various feature sets, the value of triphone modeling, etc. |
| Description: | 15th Annual Symposium of the Pattern Recognition Association of South Africa, Grabouw, South Africa, 25 to 26 November 2004 |
| URI: | http://hdl.handle.net/10204/5512 |
| Appears in Collections: | Human language technologies
General science, engineering & technology
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|
