DocumentCode
1302864
Title
Parameter re-estimation in semicontinuous hidden Markov modelling of speech with feedback to vector quantisation codebook
Author
Huang, X.D. ; Jack, M.A. ; Ariki, Yasuo
Author_Institution
Edinburgh Univ.
Volume
24
Issue
22
fYear
1988
fDate
10/27/1988 12:00:00 AM
Firstpage
1375
Lastpage
1377
Abstract
The parameters of the semicontinuous hidden Markov model (SCHMM) can be re-estimated by allowing the codebook to be updated, thus achieving an optimised codebook/model combination. With the optimised codebook, the SCHMM can offer improved recognition accuracy in comparison to both the continuous and the discrete hidden Markov model
Keywords
Markov processes; feedback; speech recognition; feedback; parameters; re-estimated; recognition accuracy; semicontinuous hidden Markov modelling; speech; vector quantisation codebook;
fLanguage
English
Journal_Title
Electronics Letters
Publisher
iet
ISSN
0013-5194
Type
jour
Filename
82449
Link To Document