Title :
Context modeling with the stochastic segment model
Author :
Kimball, O. ; Ostendorf, M. ; Bechwati, I.
Author_Institution :
Boston Univ., MA, USA
fDate :
6/1/1992 12:00:00 AM
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;
Journal_Title :
Signal Processing, IEEE Transactions on
