Tsuyoshi Morimoto

Also published as: Tsuyosi Morimoto


Statistical Method of Recognizing Local Cohesion
Naoto Katoh | Tsuyoshi Morimoto
COLING 1996 Volume 2: The 16th International Conference on Computational Linguistics


Issues in multimodal telecommunications
Tsuyoshi Morimoto
Proceedings of Machine Translation Summit V


Restructuring Tagged Corpora with Morpheme Adjustment Rules
Toshihisa Tashiro | Noriyoshi Uratani | Tsuyoshi Morimoto
COLING 1994 Volume 1: The 15th International Conference on Computational Linguistics


A Spoken Language Translation System: SL-TRANS2
Tsuyoshi Morimoto | Masami Suzuki | Toshiyuki Takezawa | Gen’ichiro Kikui | Masaaki Nagata | Mutsuko Tomokiyo
COLING 1992 Volume 3: The 14th International Conference on Computational Linguistics


Processing Unknown Words in Continuous Speech Recognition
Kenji Kita | Terumasa Ehara | Tsuyoshi Morimoto
Proceedings of the Second International Workshop on Parsing Technologies

Current continuous speech recognition systems essentially ignore unknown words. Systems are designed to recognize words in the lexicon. However, for using speech recognition systems in real applications of spoken-language processing, it is very important to process unknown words. This paper proposes a continuous speech recognition method which accepts any utterance that might include unknown words. In this method, words not in the lexicon are transcribed as phone sequences, while words in the lexicon are recognized correctly. The HMM-LR speech recognition system, which is an integration of Hidden Markov Models and generalized LR parsing, is used as the baseline system, and enhanced with the trigram model of syllables to take into account the stochastic characteristics of a language. Preliminary results indicate that our approach is very promising.


Schema Method: A Framework for Correcting Grammatically Ill-formed Input
Ikuo Kudo | Hideya Koshino | Moonkyung Chung | Tsuyosi Morimoto
Coling Budapest 1988 Volume 1: International Conference on Computational Linguistics