BYBLOS speech recognition benchmark results
HLT '91 Proceedings of the workshop on Speech and Natural Language
Integration of diverse recognition methodologies through reevaluation of N-best sentence hypotheses
HLT '91 Proceedings of the workshop on Speech and Natural Language
Recent progress in robust vocabulary-independent speech recognition
HLT '91 Proceedings of the workshop on Speech and Natural Language
The Lincoln tied-mixture HMM continuous speech recognizer
HLT '90 Proceedings of the workshop on Speech and Natural Language
Improvements in the stochastic segment model for Phoneme recognition
HLT '89 Proceedings of the workshop on Speech and Natural Language
Decision trees for phonological rules in continuous speech
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
A dynamical system approach to continuous speech recognition
ICASSP '91 Proceedings of the Acoustics, Speech, and Signal Processing, 1991. ICASSP-91., 1991 International Conference
| Hi-index | 0.00 |
This paper describes an approach for context modeling in continuous speech recognition for models based on multivariate Gaussian distributions, specifically the stochastic segment model. Typically, robust context models in HMMs are obtained by using mixture distributions; here we tie covariance parameters across classes of similar context. The specific classes over which parameters are tied can be based on models with less context or determined by clustering, where we have investigated both hand-specified linguistically motivated clusters and automatic k-means clustering. Experimental results on phoneme classification show that clustering improves performance, and word recognition results show that error reduction over context-independent models using this approach is comparable to that achieved with discrete hidden-Markov models using mixture distributions.