Context modeling with the stochastic segment model

Author

Kimball, O. ; Ostendorf, M. ; Bechwati, I.

Author_Institution

Boston Univ., MA, USA

Volume

Issue

fYear

1992

fDate

6/1/1992 12:00:00 AM

Firstpage

1584

Lastpage

1587

Abstract

An approach for context modeling in continuous speech recognition for models based on multivariate Gaussian distributions, specifically, the stochastic segment model, is described. Robust context models are obtained by typing distribution parameters across different classes of context. Experimental results in phoneme and word recognition are comparable to those achieved with discrete hidden Markov models using mixture distributions

Keywords

Markov processes; speech recognition; stochastic processes; context modeling; context models; continuous speech recognition; discrete hidden Markov models; distribution parameters; mixture distributions; multivariate Gaussian distributions; phoneme recognition; stochastic segment model; word recognition; Cepstral analysis; Context modeling; Gaussian distribution; Hidden Markov models; Power system modeling; Robustness; Speech recognition; Statistical distributions; Stochastic processes; Vectors;

fLanguage

English

Journal_Title

Signal Processing, IEEE Transactions on

Publisher

ieee

ISSN

1053-587X

Type

jour

DOI

10.1109/78.139267

Filename

139267

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1231708