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
Hi-index | 0.00 |
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.