ResearchSpace

Appropriate baseline values for HMM-based speech recognition

Show simple item record

dc.contributor.author Barnard, E
dc.contributor.author Gouws, E
dc.contributor.author Wolvaardt, K
dc.contributor.author Kleynhans, N
dc.date.accessioned 2012-01-19T10:37:27Z
dc.date.available 2012-01-19T10:37:27Z
dc.date.issued 2004-11
dc.identifier.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 en_US
dc.identifier.uri http://hdl.handle.net/10204/5512
dc.description 15th Annual Symposium of the Pattern Recognition Association of South Africa, Grabouw, South Africa, 25 to 26 November 2004 en_US
dc.description.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. en_US
dc.language.iso en en_US
dc.publisher PRASA 2004 en_US
dc.subject Hidden markov models en_US
dc.subject Pronunciation dictionaries en_US
dc.subject Human language technologies en_US
dc.subject Speech recognition en_US
dc.subject PRASA 2004 en_US
dc.subject Pattern recognition en_US
dc.title Appropriate baseline values for HMM-based speech recognition en_US
dc.type Conference Presentation en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record