M
Michael Cohen
Researcher at SRI International
Publications - 36
Citations - 1264
Michael Cohen is an academic researcher from SRI International. The author has contributed to research in topics: Hidden Markov model & Multilayer perceptron. The author has an hindex of 15, co-authored 36 publications receiving 1253 citations.
Papers
More filters
Journal ArticleDOI
Connectionist probability estimators in HMM speech recognition
TL;DR: It is shown that a connectionist component improves a state-of-the-art HMM system through a statistical interpretation of connectionist networks as probability estimators.
PatentDOI
Method for recognizing speech using linguistically-motivated hidden markov models
TL;DR: In this article, a linguistic model of words uses a state transition diagram (10) connecting states (12, 14, 16, 18, 20) with arcs (22, 24, 26, 28, 30, 32) that represent phoneme transitions within a word.
Proceedings Article
Automatic evaluation and training in English pronunciation.
TL;DR: A study of the feasibility of automati cally grading the performance of Japanese students when reading English aloud showed that ratings of speech quality by experts are very reliable and automatic grades correlate well with those expert ratings.
Proceedings Article
Connectionist speaker normalization and adaptation.
TL;DR: This paper explores supervised speaker adaptation and normalization in the MLP component of a hybrid hidden Markov model/ multilayer perceptron version of SRI's DECIPHERTM speech recognition system.
Proceedings ArticleDOI
Linguistic constraints in hidden Markov model based speech recognition
TL;DR: It is concluded that speech and linguistic knowledge sources can be used to improve the performance of HMM-based speech recognition systems provided that care is taken to incorporate these knowledge sources appropriately.