Shigeki SAGAYAMA


Bayesian Nonparametric Approach to Blind Separation of Infinitely Many Sparse Sources
Hirokazu KAMEOKA Misa SATO Takuma ONO Nobutaka ONO Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2013/10/01
Vol. E96-A  No. 10  pp. 1928-1937
Type of Manuscript:  Special Section PAPER (Special Section on Sparsity-aware Signal Processing)
Category: 
Keyword: 
underdetermined blind signal separationspeechsparsenesspermutation alignmentBayesian nonparametricsdirection of arrivalDirichlet processstick-breaking constructionvariational inference
 Summary | Full Text:PDF(3.8MB)

Discriminative Training Based on Minimum Classification Error for a Small Amount of Data Enhanced by Vector-Field-Smoothed Bayesian Learning
Jun-ichi TAKAHASHI Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1996/12/25
Vol. E79-D  No. 12  pp. 1700-1707
Type of Manuscript:  PAPER
Category: Speech Processing and Acoustics
Keyword: 
speech recognitionhidden Markov modeldiscriminative trainingspeaker adaptation
 Summary | Full Text:PDF(745.3KB)

Unsupervised Speaker Adaptation Using All-Phoneme Ergodic Hidden Markov Network
Yasunage MIYAZAWA Jun-ichi TAKAMI Shigeki SAGAYAMA Shoichi MATSUNAGA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/08/25
Vol. E78-D  No. 8  pp. 1044-1050
Type of Manuscript:  PAPER
Category: Speech Processing and Acoustics
Keyword: 
speech recognitionunsupervised speaker adaptationall-phoneme ergodic hidden Markov networkcontext-dependent phoneme bigram
 Summary | Full Text:PDF(631.1KB)

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)

Speaker-Consistent Parsing for Speaker-Independent Continuous Speech Recognition
Kouichi YAMAGUCHI Harald SINGER Shoichi MATSUNAGA Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/06/25
Vol. E78-D  No. 6  pp. 719-724
Type of Manuscript:  Special Section PAPER (Special Issue on Spoken Language Processing)
Category: 
Keyword: 
speech recognitionsearch algorithmhidden Markov modelspeaker adaptation
 Summary | Full Text:PDF(558.2KB)

Speech Recognition Using Function-Word N-Grams and Content-Word N-Grams
Ryosuke ISOTANI Shoichi MATSUNAGA Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1995/06/25
Vol. E78-D  No. 6  pp. 692-697
Type of Manuscript:  Special Section PAPER (Special Issue on Spoken Language Processing)
Category: 
Keyword: 
speech recognitionstochastic language modelN-gramfunction wordscontent words
 Summary | Full Text:PDF(534.7KB)

Spoken Sentence Recognition Based on HMM-LR with Hybrid Language Modeling
Kenji KITA Tsuyoshi MORIMOTO Kazumi OHKURA Shigeki SAGAYAMA Yaneo YANO 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1994/02/25
Vol. E77-D  No. 2  pp. 258-265
Type of Manuscript:  Special Section PAPER (Special Issue on Natural Language Processing and Understanding)
Category: 
Keyword: 
speech recognitionLR parsinghidden Markov modelHMM-LRlanguage model
 Summary | Full Text:PDF(720.1KB)

Isolated Word Recognition Using Pitch Pattern Information
Satoshi TAKAHASHI Sho-ichi MATSUNAGA Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1993/02/25
Vol. E76-A  No. 2  pp. 231-236
Type of Manuscript:  PAPER
Category: Speech
Keyword: 
word recognitionpitch patternaccent typeHMM
 Summary | Full Text:PDF(520KB)

Speaker Adaptation Based on Vector Field Smoothing
Hiroaki HATTORI Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1993/02/25
Vol. E76-D  No. 2  pp. 227-234
Type of Manuscript:  PAPER
Category: Speech Processing
Keyword: 
speech processingspeaker adaptation
 Summary | Full Text:PDF(690.5KB)

Speaker Weighted Training of HMM Using Multiple Reference Speakers
Hiroaki HATTORI Satoshi NAKAMURA Kiyohiro SHIKANO Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1993/02/25
Vol. E76-D  No. 2  pp. 219-226
Type of Manuscript:  PAPER
Category: Speech Processing
Keyword: 
speaker adaptationHMMmultiple reference speakerspeaker weight
 Summary | Full Text:PDF(675.3KB)

Three Different LR Parsing Algorithms for Phoneme-Context-Dependent HMM-Based Continuous Speech Recognition
Akito NAGAI Shigeki SAGAYAMA Kenji KITA Hideaki KIKUCHI 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1993/01/25
Vol. E76-D  No. 1  pp. 29-37
Type of Manuscript:  Special Section PAPER (Special Issue on Speech and Discourse Processing in Dialogue Systems)
Category: 
Keyword: 
speech recognitionHidden Markov ModelCFGLR parserallophonephoneme context
 Summary | Full Text:PDF(743.3KB)

LR Parsing with a Category Reachability Test Applied to Speech Recognition
Kenji KITA Tsuyoshi MORIMOTO Shigeki SAGAYAMA 
Publication:   IEICE TRANSACTIONS on Information and Systems
Publication Date: 1993/01/25
Vol. E76-D  No. 1  pp. 23-28
Type of Manuscript:  Special Section PAPER (Special Issue on Speech and Discourse Processing in Dialogue Systems)
Category: 
Keyword: 
speech recognitionHMMsLR parsingreachabilityLR-CRT algorithm
 Summary | Full Text:PDF(526.6KB)

A Study of Line Spectrum Pair Frequency Representation for Speech Recognition
Fikret S. GURGEN Shigeki SAGAYAMA Sadaoki FURUI 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1992/01/25
Vol. E75-A  No. 1  pp. 98-102
Type of Manuscript:  PAPER
Category: Speech
Keyword: 
speech recognitionline spectrum pair (LSP)transitional parameter
 Summary | Full Text:PDF(415KB)

Continuous Speech Recognition Using a Dependency Grammar and Phoneme-Based HMMs
Sho-ichi MATSUNAGA Shigeru HOMMA Shigeki SAGAYAMA Sadaoki FURUI 
Publication:   IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 1991/07/25
Vol. E74-A  No. 7  pp. 1826-1833
Type of Manuscript:  Special Section PAPER (Special Issue on Continuous Speech Recognition and Understanding)
Category: Continuous Speech Recognition
Keyword: 
 Summary | Full Text:PDF(674.8KB)