Shigeru KATAGIRI


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)

Subspace Method for Minimum Error Pattern Recognition
Hideyuki WATANABE Shigeru KATAGIRI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1997/12/25
Vol. E80-D  No. 12  pp. 1195-1204
Type of Manuscript:  PAPER
Category: Image Processing,Computer Graphics and Pattern Recognition
Keyword: 
subspace methodBayes decision theoryminimum recognition errordiscriminative traininggradient-descent search
 Summary | Full Text:PDF(801.7KB)

A Minimum Error Approach to Spotting-Based Pattern Recognition
Takashi KOMORI Shigeru KATAGIRI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/08/25
Vol. E78-D  No. 8  pp. 1032-1043
Type of Manuscript:  PAPER
Category: Speech Processing and Acoustics
Keyword: 
pattern recognitionword spottingMCE/GPDspeech recognition
 Summary | Full Text:PDF(1014.6KB)