Tetsuo KOSAKA


Unsupervised Speaker Adaptation Using Speaker-Class Models for Lecture Speech Recognition
Tetsuo KOSAKA Yuui TAKEDA Takashi ITO Masaharu KATO Masaki KOHDA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2010/09/01
Vol. E93-D  No. 9  pp. 2363-2369
Type of Manuscript:  Special Section PAPER (Special Section on Processing Natural Speech Variability for Improved Verbal Human-Computer Interaction)
Category: Adaptation
Keyword: 
speech recognitionspeaker adaptationspeaker-class modelLVCSRcorpus of spontaneous Japanese
 Summary | Full Text:PDF(393.6KB)

Robust Speech Recognition Using Discrete-Mixture HMMs
Tetsuo KOSAKA Masaharu KATOH Masaki KOHDA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 2005/12/01
Vol. E88-D  No. 12  pp. 2811-2818
Type of Manuscript:  PAPER
Category: Speech and Hearing
Keyword: 
robust speech recognitionHMMMAP estimationimpulsive noise
 Summary | Full Text:PDF(452.7KB)

Automatic Determination of the Number of Mixture Components for Continuous HMMs Based a Uniform Variance Criterion
Tetsuo KOSAKA Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/06/25
Vol. E78-D  No. 6  pp. 642-647
Type of Manuscript:  Special Section PAPER (Special Issue on Spoken Language Processing)
Category: 
Keyword: 
acoustic modelcontinuous mixture density HMMspeaker-independent speech recognitionmixture components
 Summary | Full Text:PDF(472KB)