Improvements in the stochastic segment model for Phoneme recognition

Authors:
V. Digalakis;M. Ostendorf;J. R. Rohlicek
Affiliations:
Boston University;Boston University;BBN Systems and Technologies Corp.
Venue:
HLT '89 Proceedings of the workshop on Speech and Natural Language
Year:
1989

Citing 2
Cited 5

Recognition of phonemes using time-spectrum pattern

Speech Communication - Special issue: Speech research in Japan
The acoustic-modeling problem in automatic speech recognition

The acoustic-modeling problem in automatic speech recognition

Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses

HLT '91 Proceedings of the workshop on Speech and Natural Language
A dynamical system approach to approach to continuous recognition

HLT '91 Proceedings of the workshop on Speech and Natural Language
Fast search algorithms for connected phone recognition using the stochastic segment model

HLT '90 Proceedings of the workshop on Speech and Natural Language
A multi-resolution hidden Markov model using class-specific features

IEEE Transactions on Signal Processing
Context modeling with the stochastic segment model

ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

The heart of a speech recognition system is the acoustic model of sub-word units (e.g., phonemes). In this work we discuss refinements of the stochastic segment model, an alternative to hidden Markov models for representation of the acoustic variability of phonemes. We concentrate on mechanisms for better modelling time correlation of features across an entire segment. Results are presented for speaker-independent phoneme classification in continuous speech based on the TIMIT database.