The Lincoln Continuous Speech Recognition system: recent developments and results
HLT '89 Proceedings of the workshop on Speech and Natural Language
HLT '89 Proceedings of the workshop on Speech and Natural Language
Speech recognition in SRI's resource management and ATIS systems
HLT '91 Proceedings of the workshop on Speech and Natural Language
DARPA resource management benchmark test results June 1990
HLT '90 Proceedings of the workshop on Speech and Natural Language
Improving language models by clustering training sentences
ANLC '94 Proceedings of the fourth conference on Applied natural language processing
Factorization of language constraints in speech recognition
ACL '91 Proceedings of the 29th annual meeting on Association for Computational Linguistics
Fast parsing using pruning and grammar specialization
ACL '96 Proceedings of the 34th annual meeting on Association for Computational Linguistics
Hi-index | 0.00 |
SRI has developed the DECIPHER system, a hidden Markov model (HMM) based continuous speech recognition system typically used in a speaker-independent manner. Initially we review the DECIPHER system, then we show that DECIPHER's speaker-independent performance improved by 20% when the standard 3990-sentence speaker-independent test set was augmented with training data from the 7200-sentence resource management speaker-dependent training sentences. We show a further improvement of over 20% when a version of corrective training was implemented. Finally we show improvement using parallel male- and female-trained models in DECIPHER. The word-error rate when all three improvements were combined was 3.7% on DARPA's February 1989 speaker-independent test set using the standard perplexity 60 wordpair grammar.