IEICE Trans

Shigeki SAGAYAMA

DNN-Based Full-Band Speech Synthesis Using GMM Approximation of Spectral Envelope Junya KOGUCHI Shinnosuke TAKAMICHI Masanori MORISE Hiroshi SARUWATARI Shigeki SAGAYAMA
Publication: Publication Date: 2020/12/01 Vol. E103-D No. 12 pp. 2673-2681 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: Gaussian mixture model, spectral envelope, vocoder, deep neural network, text-to-speech synthesis,
	Summary \| Full Text:PDF(1.1MB)

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 separation, speech, sparseness, permutation alignment, Bayesian nonparametrics, direction of arrival, Dirichlet process, stick-breaking construction, variational 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 recognition, hidden Markov model, discriminative training, speaker 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 recognition, unsupervised speaker adaptation, all-phoneme ergodic hidden Markov network, context-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 model, continuous mixture density HMM, speaker-independent speech recognition, mixture 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 recognition, search algorithm, hidden Markov model, speaker 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 recognition, stochastic language model, N-gram, function words, content 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 recognition, LR parsing, hidden Markov model, HMM-LR, language 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 recognition, pitch pattern, accent type, HMM,
	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 processing, speaker 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 adaptation, HMM, multiple reference speaker, speaker 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 recognition, Hidden Markov Model, CFG, LR parser, allophone, phoneme 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 recognition, HMMs, LR parsing, reachability, LR-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 recognition, line 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)