Shigeki MATSUDA


Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers
Tsubasa OCHIAI Shigeki MATSUDA Hideyuki WATANABE Xugang LU Chiori HORI Hisashi KAWAI Shigeru KATAGIRI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2016/10/01
Vol. E99-D  No. 10  pp. 2431-2443
Type of Manuscript:  Special Section PAPER (Special Section on Recent Advances in Machine Learning for Spoken Language Processing)
Category: Acoustic modeling
Keyword: 
Deep Neural NetworksHybrid DNN-HMMSpeaker AdaptationSpeaker Adaptive Training
 Summary | Full Text:PDF(923.4KB)

ATR Parallel Decoding Based Speech Recognition System Robust to Noise and Speaking Styles
Shigeki MATSUDA Takatoshi JITSUHIRO Konstantin MARKOV Satoshi NAKAMURA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2006/03/01
Vol. E89-D  No. 3  pp. 989-997
Type of Manuscript:  Special Section PAPER (Special Section on Statistical Modeling for Speech Processing)
Category: Speech Recognition
Keyword: 
automatic speech recognitionparallel decodingmultiple acoustic modelsfast noise adaptationspeaking stylehyper-articulated speech
 Summary | Full Text:PDF(644KB)