On the interaction between true source, training, and testing language models
HLT '90 Proceedings of the workshop on Speech and Natural Language
Continuous speech recognition from a phonetic transcription
HLT '90 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
Training set issues in SRI's DECIPHER speech recognition system
HLT '90 Proceedings of the workshop on Speech and Natural Language
Improved HMM models for high performance speech recognition
HLT '89 Proceedings of the workshop on Speech and Natural Language
HLT '89 Proceedings of the workshop on Speech and Natural Language
Tied mixtures in the Lincoln robust CSR
HLT '89 Proceedings of the workshop on Speech and Natural Language
Prosody, performance evaluation, databases, and ISAT
HLT '89 Proceedings of the workshop on Speech and Natural Language
Hi-index | 0.00 |
The Lincoln stress-resistant HMM CSR has been extended to large vocabulary continuous speech for both speaker-dependent (SD) and speaker-independent (SI) tasks. Performance on the DARPA Resource Management task (991 word vocabulary, perplexity 60 word-pair grammar) [1] is 3.4% word error rate for SD training of word-context-dependent triphone models and 12.6% word error rate for SI training of (word-context-free) tied mixture triphone models.