| Co-Investigator(Kenkyū-buntansha) |
UMESAKI Taizo Chubu University, Faculty of Engineering Lecturer, 工学部, 講師 (40193932)
DANTSUJI Masatake Kansai University, Faculty of Letters Associate Professor, 文学部, 助教授 (10188469)
KITAZAWA Shigeyoshi Shizuoka University, Faculty of Engneering Associate Professor, 工学部, 助教授 (00109018)
KOBAYASHI Yutaka Kyoto Institute of Technology, Faculty of Engineering and Design Assistant, 工芸学部, 助手 (40027917)
NIIMI Yasuhisa Kyoto Institute of Technology, Faculty of Engineering and Design Professor, 工芸学部, 教授 (00026030)
|
|---|
| Research Abstract |
Primary outcomes are in the following :
(a) in the field of hidden Markov model
Speaker adaptation of continuous HMM, combination of HMM and segmental statistics, consideration on semi-continuous HMM, new matrix-based calculation method for HMM, automatic construction of context-dependent HMM, learing of HMM by generalized descendent method,
(b) in the field of neural network
spoken word recognition by sequential neural network (neural Markov model), consideration on feed-forward neural network for pattern recognition (dimensionality reduction, estimation of probability density function). generalized sequential machine. theoretical analysis for approximation of continuous function by recurrent neural network
(c) in the field of acoustic/phonology and feature extraction
new acoustic feature model and feature hierarchies, extraction of distinctive feature by neural network, evaluation of smoothed group delay spectrum distance measure.
(d) in the field of language model
modeling of natural language by bigram/trigram/HMM/stochastic CFG, continuous stochastic CFG, analysis of phenomena in spoken dialog, sentence generation for QA system.
(e) in the field of continuous speech recognition system
context-free grammar driven time synchronous continuous speech recognition using HMM, segmented trellis HMM calculation algorithm for continuous speech recognition, LR - HMM based continuous speech recognizor
|
