Continuously variable duration hidden Markov models for automatic speech recognition
Computer Speech and Language
Continuous speech recognition from a phonetic transcription
HLT '90 Proceedings of the workshop on Speech and Natural Language
Factorization of language constraints in speech recognition
ACL '91 Proceedings of the 29th annual meeting on Association for Computational Linguistics
Broad phonetic classification using discriminative Bayesian networks
Speech Communication
On supervision and statistical learning for semantic multimedia analysis
Journal of Visual Communication and Image Representation
Experiments on speaker-independent phone recognition using BREF
ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
| Hi-index | 0.00 |
Speaker independent phonetic transcription of fluent speech is performed using an ergodic continuously variable duration hidden Markov model (CVDHMM) to represent the acoustic, phonetic and phonotactic structure of speech. An important property of the model is that each of its fifty-one states is uniquely identified with a single phonetic unit. Thus, for any spoken utterance, a phonetic transcription is obtained from a dynamic programming (DP) procedure for finding the state sequence of maximum likelihood. A model has been constructed based on 4020 sentences from the TIMIT database. When tested on 180 different sentences from this database, phonetic accuracy was observed to be 56% with 9% insertions. A speaker dependent version of the model was also constructed. The transcription algorithm was then combined with lexical access and parsing routines to form a complete recognition system. When tested on sentences from the DARPA resource management task spoken over the local switched telephone network, phonetic accuracy of 64% with 8% insertions and word accuracy of 87% with 3% insertions was measured. This system is presently operating in an on-line mode over the local switched telephone network in less than ten times real time on an Alliant FX-80.