DocumentCode
3015763
Title
Explicit time correlation in hidden Markov models for speech recognition
Author
Wellekens, C.J.
Author_Institution
Philips Research Laboratory, Brussels, Belgium
Volume
12
fYear
1987
fDate
31868
Firstpage
384
Lastpage
386
Abstract
The Hidden Markov models are generalized by defining a new emission probability which takes the correlation between successive feature vectors into account. Estimation formulas for the iterative learning both along Viterbi and Maximum likelihood criteria are presented.
Keywords
Hidden Markov models; Maximum likelihood estimation; Speech recognition; State estimation; Symmetric matrices; TV; Viterbi algorithm; Yield estimation;
fLanguage
English
Publisher
ieee
Conference_Titel
Acoustics, Speech, and Signal Processing, IEEE International Conference on ICASSP '87.
Type
conf
DOI
10.1109/ICASSP.1987.1169614
Filename
1169614
Link To Document