DocumentCode :
323759
Title :
Training of subspace distribution clustering hidden Markov model
Author :
Mak, Brian ; Bocchieri, Enrico
Author_Institution :
AT&T Labs., Florham Park, NJ, USA
Volume :
2
fYear :
1998
fDate :
12-15 May 1998
Firstpage :
673
Abstract :
Levinson, Juang and Sondhi (1986), and Mak, Bocchieri, and E. Barnard (see Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 1997) presented novel subspace distribution clustering hidden Markov models (SDCHMMs) which can be converted from continuous density hidden Markov models (CDHMMs) by clustering subspace Gaussians in each stream over all models. Though such model conversion is simple and runs fast, it has two drawbacks: (1) it does not take advantage of the fewer model parameters in SDCHMMs-theoretically SDCHMMs may be trained with smaller amount of data; and, (2) it involves two separate optimization steps (first training CDHMMs, then clustering subspace Gaussians) and the resulting SDCHMMs are not guaranteed to be optimal. We show how SDCHMMs may be trained directly from less speech data if we have a priori knowledge of their architecture. On the ATIS task, a speaker-independent, context-independent (CI) 20-stream SDCHMM system trained using our novel SDCHMM reestimation algorithm with only 8 minutes of speech performs as well as a CDHMM system trained using conventional CDHMM reestimation algorithm with 105 minutes of speech
Keywords :
Gaussian distribution; hidden Markov models; parameter estimation; pattern recognition; speech recognition; 105 min; 8 min; ATIS task; CDHMM reestimation algorithm; SDCHMM reestimation algorithm; acoustic modelling; context-independent speech recognition; continuous density hidden Markov models; model conversion; optimization steps; speaker-independent system; speech data; subspace Gaussians clustering; subspace distribution clustering HMM; training; Gaussian processes; Hidden Markov models; Signal processing; Speech recognition; Testing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on
Conference_Location :
Seattle, WA
ISSN :
1520-6149
Print_ISBN :
0-7803-4428-6
Type :
conf
DOI :
10.1109/ICASSP.1998.675354
Filename :
675354
Link To Document :
بازگشت