IEICE Trans

Keiichi TOKUDA

A Bayesian Approach to Image Recognition Based on Separable Lattice Hidden Markov Models Kei SAWADA Akira TAMAMORI Kei HASHIMOTO Yoshihiko NANKAKU Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2016/12/01 Vol. E99-D No. 12 pp. 3119-3131 Type of Manuscript: PAPER Category: Pattern Recognition Keyword: image recognition, hidden Markov models, separable lattice hidden Markov models, Bayesian approach, deterministic annealing,
	Summary \| Full Text:PDF(972.5KB)

Image Recognition Based on Separable Lattice Trajectory 2-D HMMs Akira TAMAMORI Yoshihiko NANKAKU Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2014/07/01 Vol. E97-D No. 7 pp. 1842-1854 Type of Manuscript: PAPER Category: Pattern Recognition Keyword: image recognition, hidden Markov models, separable lattice 2-D HMMs, trajectory HMMs,
	Summary \| Full Text:PDF(1.6MB)

Integration of Spectral Feature Extraction and Modeling for HMM-Based Speech Synthesis Kazuhiro NAKAMURA Kei HASHIMOTO Yoshihiko NANKAKU Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2014/06/01 Vol. E97-D No. 6 pp. 1438-1448 Type of Manuscript: Special Section PAPER (Special Section on Advances in Modeling for Real-world Speech Information Processing and its Application) Category: HMM-based Speech Synthesis Keyword: integrative model, HMM-based speech synthesis, acoustic modeling, mel-cepstral analysis, trajectory HMM,
	Summary \| Full Text:PDF(1.7MB)

A Bayesian Framework Using Multiple Model Structures for Speech Recognition Sayaka SHIOTA Kei HASHIMOTO Yoshihiko NANKAKU Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2013/04/01 Vol. E96-D No. 4 pp. 939-948 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: speech recognition, acoustic modeling, Bayesian approach, model structure integration, deterministic annealing,
	Summary \| Full Text:PDF(548.8KB)

An Extension of Separable Lattice 2-D HMMs for Rotational Data Variations Akira TAMAMORI Yoshihiko NANKAKU Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2012/08/01 Vol. E95-D No. 8 pp. 2074-2083 Type of Manuscript: PAPER Category: Pattern Recognition Keyword: image recognition, hidden Markov models, variational method,
	Summary \| Full Text:PDF(1.3MB)

Bayesian Context Clustering Using Cross Validation for Speech Recognition Kei HASHIMOTO Heiga ZEN Yoshihiko NANKAKU Akinobu LEE Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2011/03/01 Vol. E94-D No. 3 pp. 668-678 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: Bayesian approach, speech recognition, HMM, context clustering, cross validation,
	Summary \| Full Text:PDF(453.4KB)

A Covariance-Tying Technique for HMM-Based Speech Synthesis Keiichiro OURA Heiga ZEN Yoshihiko NANKAKU Akinobu LEE Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2010/03/01 Vol. E93-D No. 3 pp. 595-601 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: HMM, speech synthesis, decision tree, context-clustering, MDL criterion, embedded device,
	Summary \| Full Text:PDF(662.9KB)

A Reordering Model Using a Source-Side Parse-Tree for Statistical Machine Translation Kei HASHIMOTO Hirofumi YAMAMOTO Hideo OKUMA Eiichiro SUMITA Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2009/12/01 Vol. E92-D No. 12 pp. 2386-2393 Type of Manuscript: Special Section PAPER (Special Section on Natural Language Processing and its Applications) Category: Machine Translation Keyword: phrase-based statistical machine translation, reordering model, parse-tree, syntactic information,
	Summary \| Full Text:PDF(254.4KB)

A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System Keiichiro OURA Heiga ZEN Yoshihiko NANKAKU Akinobu LEE Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2008/11/01 Vol. E91-D No. 11 pp. 2693-2700 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: speech recognition, hidden Markov model, hidden semi-Markov model, weighted finite-state transducer,
	Summary \| Full Text:PDF(531.3KB)

The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006 Heiga ZEN Tomoki TODA Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2008/06/01 Vol. E91-D No. 6 pp. 1764-1773 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: statistical parametric speech synthesis, Blizzard Challenge 2006, MGC-LSP, MLLT, full covariance GV pdf,
	Summary \| Full Text:PDF(1.4MB)

A Hidden Semi-Markov Model-Based Speech Synthesis System Heiga ZEN Keiichi TOKUDA Takashi MASUKO Takao KOBAYASIH Tadashi KITAMURA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2007/05/01 Vol. E90-D No. 5 pp. 825-834 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: hidden Markov model, hidden semi-Markov model, HMM-based speech synthesis,
	Summary \| Full Text:PDF(452.5KB)

A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis Tomoki TODA Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2007/05/01 Vol. E90-D No. 5 pp. 816-824 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: HMM-based speech synthesis, speech parameter generation, maximum likelihood criterion, over-smoothing effect, global variance,
	Summary \| Full Text:PDF(1.2MB)

State Duration Modeling for HMM-Based Speech Synthesis Heiga ZEN Takashi MASUKO Keiichi TOKUDA Takayoshi YOSHIMURA Takao KOBAYASIH Tadashi KITAMURA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2007/03/01 Vol. E90-D No. 3 pp. 692-693 Type of Manuscript: LETTER Category: Speech and Hearing Keyword: duration modeling, speech synthesis, hidden Markov model,
	Summary \| Full Text:PDF(54.1KB)

Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005 Heiga ZEN Tomoki TODA Masaru NAKAMURA Keiichi TOKUDA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2007/01/01 Vol. E90-D No. 1 pp. 325-333 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: HMM-based speech synthesis, Blizzard Challenge 2005, STRAIGHT, HSMM, GV,
	Summary \| Full Text:PDF(700KB)

Continuous Speech Recognition Based on General Factor Dependent Acoustic Models Hiroyuki SUZUKI Heiga ZEN Yoshihiko NANKAKU Chiyomi MIYAJIMA Keiichi TOKUDA Tadashi KITAMURA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2005/03/01 Vol. E88-D No. 3 pp. 410-417 Type of Manuscript: Special Section PAPER (Special Section on Corpus-Based Speech Technologies) Category: Feature Extraction and Acoustic Medelings Keyword: continuous speech recognition, triphone HMMs, context clustering, Bayesian networks, voice characteristic, noise environment,
	Summary \| Full Text:PDF(487.4KB)

Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition Yohei ITAYA Heiga ZEN Yoshihiko NANKAKU Chiyomi MIYAJIMA Keiichi TOKUDA Tadashi KITAMURA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2005/03/01 Vol. E88-D No. 3 pp. 425-431 Type of Manuscript: Special Section PAPER (Special Section on Corpus-Based Speech Technologies) Category: Feature Extraction and Acoustic Medelings Keyword: DAEM algorithm, acoustic modeling, EM algorithm, GMMs, HMMs,
	Summary \| Full Text:PDF(680.4KB)

Applying Sparse KPCA for Feature Extraction in Speech Recognition Amaro LIMA Heiga ZEN Yoshihiko NANKAKU Keiichi TOKUDA Tadashi KITAMURA Fernando G. RESENDE
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2005/03/01 Vol. E88-D No. 3 pp. 401-409 Type of Manuscript: Special Section PAPER (Special Section on Corpus-Based Speech Technologies) Category: Feature Extraction and Acoustic Medelings Keyword: kernel, sparsity, principal component analysis, feature extraction, speech recognition,
	Summary \| Full Text:PDF(582.4KB)

Parameter Sharing in Mixture of Factor Analyzers for Speaker Identification Hiroyoshi YAMAMOTO Yoshihiko NANKAKU Chiyomi MIYAJIMA Keiichi TOKUDA Tadashi KITAMURA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2005/03/01 Vol. E88-D No. 3 pp. 418-424 Type of Manuscript: Special Section PAPER (Special Section on Corpus-Based Speech Technologies) Category: Feature Extraction and Acoustic Medelings Keyword: speaker identification, GMM, mixture of factor analyzers, parameter sharing, minimum classification error training,
	Summary \| Full Text:PDF(545.3KB)

On the Use of Kernel PCA for Feature Extraction in Speech Recognition Amaro LIMA Heiga ZEN Yoshihiko NANKAKU Chiyomi MIYAJIMA Keiichi TOKUDA Tadashi KITAMURA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2004/12/01 Vol. E87-D No. 12 pp. 2802-2811 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: kernel, feature space, principal component analysis, feature extraction, speech recognition,
	Summary \| Full Text:PDF(425.6KB)

Mixture Density Models Based on Mel-Cepstral Representation of Gaussian Process Toru TAKAHASHI Keiichi TOKUDA Takao KOBAYASHI Tadashi KITAMURA
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 2003/08/01 Vol. E86-A No. 8 pp. 1971-1978 Type of Manuscript: Special Section PAPER (Special Section on Digital Signal Processing) Category: Keyword: Gaussian mixture model, statistical framework, mel-cepstrum, EM algorithm,
	Summary \| Full Text:PDF(1MB)

A Training Method of Average Voice Model for HMM-Based Speech Synthesis Junichi YAMAGISHI Masatsune TAMURA Takashi MASUKO Keiichi TOKUDA Takao KOBAYASHI
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 2003/08/01 Vol. E86-A No. 8 pp. 1956-1963 Type of Manuscript: Special Section PAPER (Special Section on Digital Signal Processing) Category: Keyword: decision tree, context clustering, speaker adaptation, speaker adaptive training, average voice model, HMM-based speech synthesis,
	Summary \| Full Text:PDF(599.3KB)

A Context Clustering Technique for Average Voice Models Junichi YAMAGISHI Masatsune TAMURA Takashi MASUKO Keiichi TOKUDA Takao KOBAYASHI
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2003/03/01 Vol. E86-D No. 3 pp. 534-542 Type of Manuscript: Special Section PAPER (Special Issue on Speech Information Processing) Category: Speech Synthesis and Prosody Keyword: decision tree, context clustering, average voice model, HMM-based speech synthesis, speaker independent model,
	Summary \| Full Text:PDF(752.9KB)

Multi-Space Probability Distribution HMM Keiichi TOKUDA Takashi MASUKO Noboru MIYAZAKI Takao KOBAYASHI
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2002/03/01 Vol. E85-D No. 3 pp. 455-464 Type of Manuscript: INVITED PAPER (Special Issue on the 2000 IEICE Excellent Paper Award) Category: Pattern Recognition Keyword: hidden Markov model, text-to-speech, F0, multi-space probability distribution,
	Summary \| Full Text:PDF(624.5KB)

Vector Quantization of Speech Spectral Parameters Using Statistics of Static and Dynamic Features Kazuhito KOISHIDA Keiichi TOKUDA Takashi MASUKO Takao KOBAYASHI
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2001/10/01 Vol. E84-D No. 10 pp. 1427-1434 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: vector quantization, dynamic features, spectral quantization, LSP parameters,
	Summary \| Full Text:PDF(640.5KB)

Text-Independent Speaker Identification Using Gaussian Mixture Models Based on Multi-Space Probability Distribution Chiyomi MIYAJIMA Yosuke HATTORI Keiichi TOKUDA Takashi MASUKO Takao KOBAYASHI Tadashi KITAMURA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2001/07/01 Vol. E84-D No. 7 pp. 847-855 Type of Manuscript: Special Section PAPER (Special Issue on Biometric Person Authentication) Category: Keyword: speaker identification, pitch, multi-space probability distribution, Gaussian mixture model (GMM), minimum classification error,
	Summary \| Full Text:PDF(921.7KB)

Lip Location Normalized Training for Visual Speech Recognition Oscar VANEGAS Keiichi TOKUDA Tadashi KITAMURA
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2000/11/25 Vol. E83-D No. 11 pp. 1969-1977 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: hidden Markov model, lip location normalization, lipreading, Tulips1, M2VTS,
	Summary \| Full Text:PDF(2.4MB)

A 16 kb/s Wideband CELP-Based Speech Coder Using Mel-Generalized Cepstral Analysis Kazuhito KOISHIDA Gou HIRABAYASHI Keiichi TOKUDA Takao KOBAYASHI
Publication: IEICE TRANSACTIONS on Information and Systems Publication Date: 2000/04/25 Vol. E83-D No. 4 pp. 876-883 Type of Manuscript: PAPER Category: Speech and Hearing Keyword: wideband speech coding, mel-generalized cepstral analysis, mel-generalized cepstrum, CELP coding,
	Summary \| Full Text:PDF(693.7KB)

LMS-Based Algorithms with Multi-Band Decomposition of the Estimation Error Applied to System Identification Fernando Gil V. RESENDE,Jr Paulo S.R. DINIZ Keiichi TOKUDA Mineo KANEKO Akinori NISHIHARA
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 1997/08/25 Vol. E80-A No. 8 pp. 1376-1383 Type of Manuscript: Special Section PAPER (Special Section on Digital Signal Processing) Category: Keyword: adaptive signal processing, fixed and variable step-size LMS algorithms, filter banks, system identification,
	Summary \| Full Text:PDF(629.5KB)

Multi-Band Decomposition of the Linear Prediction Error Applied to Adaptive AR Spectral Estimation Fernando Gil V. RESENDE Jr. Keiichi TOKUDA Mineo KANEKO Akinori NISHIHARA
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 1997/02/25 Vol. E80-A No. 2 pp. 365-376 Type of Manuscript: PAPER Category: Digital Signal Processing Keyword: digital signal processing, AR spectral estimation, filter banks, adaptive filtering, recursive least-squares algorithms,
	Summary \| Full Text:PDF(902.1KB)

Adaptive AR Spectral Estimation Based on Wavelet Decomposition of the Linear Prediction Error Fernando Gil V. RESENDE Jr. Keiichi TOKUDA Mineo KANEKO
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 1996/05/25 Vol. E79-A No. 5 pp. 665-673 Type of Manuscript: PAPER Category: Digital Signal Processing Keyword: digital signal processing, spectral etimation, wavelet theory, adaptive fultering, recursive least-squares algorithms,
	Summary \| Full Text:PDF(725.7KB)

Time Series Analysis Based on Exponential Model Excited by t-Distribution Process and Its Algorithm Junibakti SANUBARI Keiichi TOKUDA Mahoki ONODA
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 1993/05/25 Vol. E76-A No. 5 pp. 808-819 Type of Manuscript: PAPER Category: Digital Signal Processing Keyword: exponential model, t-distribution, M-estimate, time series analysis, finite-length cepstrum,
	Summary \| Full Text:PDF(788.1KB)

Speech Analysis Based on AR Model Driven by t-Distribution Process Junibakti SANUBARI Keiichi TOKUDA Mahoki ONODA
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 1992/09/25 Vol. E75-A No. 9 pp. 1159-1169 Type of Manuscript: PAPER Category: Speech Keyword: AR modeling, t-distribution, M-estimate, speech analysis,
	Summary \| Full Text:PDF(749.9KB)

2-D LMA Filters--Design of Stable Two-Dimensional Digital Filters with Arbitrary Magnitude Function-- Takao KOBAYASHI Kazuyoshi FUKUSHI Keiichi TOKUDA Satoshi IMAI
Publication: IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences Publication Date: 1992/02/25 Vol. E75-A No. 2 pp. 240-246 Type of Manuscript: PAPER Category: Digital Image Processing Keyword: 2-D digital filter, LMA filter, 2-D spectral factorization,
	Summary \| Full Text:PDF(507.3KB)