Keiichi Tokuda

发表

Spectral conversion based on statistical models including time-sequence matching

Yoshihiko Nankaku, Keiichi Tokuda, Tomoki Toda, 2007, SSW.

Text-to-visual speech synthesis based on parameter generation from HMM

Keiichi Tokuda, Takao Kobayashi, Masatsune Tamura, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

An adaptive algorithm for mel-cepstral analysis of speech

Keiichi Tokuda, Takao Kobayashi, T. Fukada, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Integration of acoustic modeling and mel-cepstral analysis for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kazuhiro Nakamura, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Deterministic Annealing EM Algorithm in Acoustic Modeling for Speaker and Speech Recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005, IEICE Trans. Inf. Syst..

A bayesian framework for image recognition based on hidden markov eigen‐image models

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING.

Estimation of Perceptual Spaces for Speaker Identities Based on the Cross-Lingual Discrimination Task

Keiichi Tokuda, Hisashi Kawai, Jinfu Ni, 2011, INTERSPEECH.

Simultaneous optimization of multiple tree structures for factor analyzed HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2015, INTERSPEECH.

Speech Synthesis Using WaveNet Vocoder Based on Periodic/Aperiodic Decomposition

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2007, SSW.

Discriminative Feature Extraction Based on Sequential Variational Autoencoder for Speaker Recognition

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

A robust speaker verification system against imposture using an HMM-based speech synthesis system

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2001, INTERSPEECH.

Trajectory training considering global variance for speech synthesis based on neural networks

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Incorporating a mixed excitation model and postfilter into HMM-based text-to-speech synthesis

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2005 .

Intensity/location normalization for automatic lipreading

Keiichi Tokuda, Tadashi Kitamura, A. Tanaka, 1998, ICSP '98. 1998 Fourth International Conference on Signal Processing (Cat. No.98TH8344).

Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis

Heiga Zen, Keiichi Tokuda, H. Zen, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

An HMM-based singing voice synthesis system

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2006, INTERSPEECH.

Singing Voice Synthesis Based on Deep Neural Networks

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2016, INTERSPEECH.

Image recognition based on separable lattice trajectory 2-D HMMS

Yoshihiko Nankaku, Keiichi Tokuda, Akira Tamamori, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Adaptive filtering based on cepstral representation-adaptive cepstral analysis of speech

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 1990, International Conference on Acoustics, Speech, and Signal Processing.

Face recognition based on extended separable lattice 2-D HMMS

Yoshihiko Nankaku, Keiichi Tokuda, Keisuke Kumaki, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Sparse KPCA for feature extraction in speech recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Face recognition based on separable lattice 2-D HMM with state duration modeling

Yoshihiko Nankaku, Keiichi Tokuda, Yoshiaki Takahashi, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Estimation of Window Coefficients for Dynamic Feature Extraction for HMM-Based Speech Synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2011, INTERSPEECH.

Image recognition based on separable lattice trajectory 2-D HMMS

Yoshihiko Nankaku, Keiichi Tokuda, Akira Tamamori, 2013, IEEE International Conference on Acoustics, Speech, and Signal Processing.

A trainable singing voice synthesis system capable of representing personal characteristics and singing styles

Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, 2008 .

Statistical Parametric Speech Synthesis

Heiga Zen, Keiichi Tokuda, Alan W. Black, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

A wideband CELP speech coder at 16 kbit/s based on mel-generalized cepstral analysis

Keiichi Tokuda, Takao Kobayashi, Kazuhito Koishida, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

Trajectory modeling based on HMMs with the explicit relationship between static and dynamic features

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2003, INTERSPEECH.

Voice conversion based on mixtures of factor analyzers

Yoshihiko Nankaku, Keiichi Tokuda, Tomoki Toda, 2006, INTERSPEECH.

Using speaker adaptive training to realize Mandarin-Tibetan cross-lingual speech synthesis

Keiichi Tokuda, Haiyan Wang, Zhenye Gan, 2014, Multimedia Tools and Applications.

Robust two dimensional spectral estimation based on AR model excited by a t-distribution process

Keiichi Tokuda, Junibakti Sanubari, Mahoki Onoda, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

CELP coding based on mel-cepstral analysis

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 1995, 1995 International Conference on Acoustics, Speech, and Signal Processing.

Reducing computation on parallel decoding using frame-wise confidence scores

Yoshihiko Nankaku, Keiichi Tokuda, Akinobu Lee, 2006, Interspeech.

The NICT Entry for the Blizzard Challenge 2009: an Enhanced HMM-based Speech Synthesis System with Trajectory Training Considering Global Variance and State-Dependent Mixed Excitation

Keiichi Tokuda, Tomoki Toda, Satoshi Nakamura, 2009 .

Life-Like Characters. Tools, Affective Functions, and Applications

Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, 2003 .

HMM-Based singing voice synthesis and its application to Japanese and English

Yoshihiko Nankaku, Keiichi Tokuda, Kazuhiro Nakamura, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

LMS-like two dimensional adaptive filter with t-distribution assumption and nonsymmetrical half-plane support

Keiichi Tokuda, Junibakti Sanubari, 1999, NSIP.

A training method for average voice model based on shared decision tree context clustering and speaker adaptive training

Keiichi Tokuda, Takao Kobayashi, Junichi Yamagishi, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

A Bayesian Approach to Image Recognition Based on Separable Lattice Hidden Markov Models

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2016, IEICE Trans. Inf. Syst..

Impacts of machine translation and speech synthesis on speech-to-speech translation

Keiichi Tokuda, William J. Byrne, Simon King, 2012, Speech Commun..

Voice characteristics conversion for HMM-based speech synthesis system

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

A Viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Normalized training for HMM-based visual speech recognition

Yoshihiko Nankaku, Keiichi Tokuda, Takao Kobayashi, 2000, Proceedings 2000 International Conference on Image Processing (Cat. No.00CH37101).

A Singing Voice Synthesis System Based on Hidden Markov Model

Keiichi Tokuda, Tadashi Kitamura, Chiyomi Miyajima, 2003 .

An extension of Separable Lattice 2-D HMMS for rotational data variations

Yoshihiko Nankaku, Keiichi Tokuda, Akira Tamamori, 2010, ICASSP 2010.

A Bayesian approach to Hidden Semi-Markov Model based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2009, INTERSPEECH.

Singing Voice Conversion Using Posted Waveform Data on Music Social Media

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Spectral estimation based on AR-model excited by t-distribution process

Keiichi Tokuda, J. Sanubari, M. Onoda, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Multi-Speaker Modeling with Shared Prior Distributions and Model Structures for Bayesian Speech Synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2011, INTERSPEECH.

A Hidden Semi-Markov Model-Based Speech Synthesis System

Heiga Zen, Keiichi Tokuda, Takao Kobayashi, 2007, IEICE Trans. Inf. Syst..

HMM-based singing voice synthesis system using pitch-shifted pseudo training data

Yoshihiko Nankaku, Keiichi Tokuda, Keiichiro Oura, 2010, INTERSPEECH.

Directly modeling voiced and unvoiced components in speech waveforms by neural networks

Heiga Zen, Keiichi Tokuda, H. Zen, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

XIMERA: a new TTS from ATR based on corpus-based technologies

Keiichi Tokuda, Tomoki Toda, Hisashi Kawai, 2004, SSW.

Fast convergence transversal adaptive filtering algorithm for impulsive environment based on T distribution assumption

Keiichi Tokuda, Junibakti Sanubari, 2001, ISCAS 2001. The 2001 IEEE International Symposium on Circuits and Systems (Cat. No.01CH37196).

A Hierarchical Predictor of Synthetic Speech Naturalness Using Neural Networks

Keiichi Tokuda, Oliver Watts, Junichi Yamagishi, 2016, INTERSPEECH.

AR spectrum estimation based on wavelet representation

Keiichi Tokuda, Mineo Kaneko, Fernando Gil Vianna Resende, 1994, Proceedings of IEEE International Symposium on Circuits and Systems - ISCAS '94.

Speech synthesis using HMMs with dynamic features

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1996, 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings.

Robust recursive spectral estimation based on an AR model excited by a t-distribution process by using QR decomposition algorithm

Keiichi Tokuda, J. Sanubari, 1997, Proceedings of 1997 IEEE International Symposium on Circuits and Systems. Circuits and Systems in the Information Age ISCAS '97.

Details of the Nitech HMM-Based Speech Synthesis System for the Blizzard Challenge 2005

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2007, IEICE Trans. Inf. Syst..

Improving the performance of HMM-based very low bit rate speech coding

Heiga Zen, Keiichi Tokuda, Takao Kobayashi, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Bayesian speech synthesis framework integrating training and synthesis processes

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2010, SSW.

Face Recognition using Hidden Markov Eigenface Models

Yoshihiko Nankaku, Keiichi Tokuda, K. Tokuda, 2007, 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07.

Mel-Cepstrum-Based Quantization Noise Shaping Applied to Neural-Network-Based Speech Waveform Synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Speaker adaptation and the evaluation of speaker similarity in the EMIME speech-to-speech translation project

Keiichi Tokuda, Mikko Kurimo, William J. Byrne, 2010, SSW.

A context clustering technique for average voice model in HMM-based speech synthesis

Keiichi Tokuda, Takao Kobayashi, Masatsune Tamura, 2002, INTERSPEECH.

Deterministic annealing EM algorithm in parameter estimation for acoustic model

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2004, INTERSPEECH.

Voice interaction system with 3D-CG virtual agent for stand-alone smartphones

Keiichi Tokuda, Daisuke Yamamoto, Takahiro Uchiya, 2014, HAI.

Model-space MLLR for trajectory HMMs

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2007, INTERSPEECH.

Proceedings of the ACL 2010 System Demonstrations

Keiichi Tokuda, Mikko Kurimo, Simon King, 2010 .

NICT Blizzard Challenge 2010 Entry

Keiichi Tokuda, Satoshi Nakamura, Hisashi Kawai, 2010 .

Duration modeling for HMM-based speech synthesis

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 1998, ICSLP.

User Generated Dialogue Systems: uDialogue

Yoshihiko Nankaku, Keiichi Tokuda, Junichi Yamagishi, 2017, Human-Harmonized Information Technology.

Speaker-dependent Wavenet-based Delay-free Adpcm Speech Coding

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Hidden Semi-Markov Model Based Speech Recognition System using Weighted Finite-State Transducer

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Spectral conversion based on maximum likelihood estimation considering global variance of converted parameter

Keiichi Tokuda, Tomoki Toda, Alan W. Black, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Image Recognition Based on Convolutional Neural Networks Using Features Generated from Separable Lattice Hidden Markov Models

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Speaker-Independent HMM-based Speech Synthesis System: HTS-2007 System for the Blizzard Challenge 2007

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2007 .

A decision tree-based clustering approach to state definition in an excitation modeling framework for HMM-based speech synthesis

Keiichi Tokuda, Tomoki Toda, Satoshi Nakamura, 2009, INTERSPEECH.

HMM-based european Portuguese TTS system

Keiichi Tokuda, Ranniery Maia, Diamantino Freitas, 2005, INTERSPEECH.

A Deterministic Annealing-Based Training Algorithm For Statistical Machine Translation Models

Yoshihiko Nankaku, Keiichi Tokuda, Pascual Martínez-Gómez, 2010, EAMT.

Cross-lingual speaker adaptation based on factor analysis using bilingual speech data for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2013, SSW.

Speaker adaptation of pitch and spectrum for HMM-based speech synthesis

Keiichi Tokuda, Takao Kobayashi, Masatsune Tamura, 2002, Systems and Computers in Japan.

ATRECSS — ATR ENGLISH SPEECH CORPUS FOR SPEECH SYNTHESIS

Keiichi Tokuda, Tomoki Toda, Satoshi Nakamura, 2007 .

Galatea: Open-Source Software for Developing Anthropomorphic Spoken Dialog Agents

Keiichi Tokuda, Keikichi Hirose, Nobuaki Minematsu, 2004, Life-like characters.

Redefining the Linguistic Context Feature Set for HMM and DNN TTS Through Position and Parsing

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2016, INTERSPEECH.

Factor analyzed voice models for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kyosuke Kazumi, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Communicative speech synthesis with XIMERA: a first step

Keiichi Tokuda, Tomoki Toda, Satoshi Nakamura, 2007, SSW.

Impacts of input linguistic feature representation on Japanese end-to-end speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2019 .

Imposture against a Speaker Verification System Using Synthetic Speech

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2000 .

An algorithm for speech parameter generation from continuous mixture HMMs with dynamic features

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1995, EUROSPEECH.

Integration of Spectral Feature Extraction and Modeling for HMM-Based Speech Synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kazuhiro Nakamura, 2014, IEICE Trans. Inf. Syst..

A 16kb/s Wideband CELP-Based Speech Coder Using Mel-Generalized Cepstral Analysis

Keiichi Tokuda, Takao Kobayashi, Kazuhito Koishida, 2000 .

Unsupervised adaptation for HMM-based speech synthesis

Heiga Zen, Keiichi Tokuda, Simon King, 2008, INTERSPEECH.

Investigation of State Duration Model based on Gamma distribution for HMM-based Speech Synthesis

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 2001 .

The blizzard challenge - 2005: evaluating corpus-based speech synthesis on common datasets

Keiichi Tokuda, Alan W. Black, K. Tokuda, 2005, INTERSPEECH.

Decision tree-based simultaneous clustering of phonetic contexts, dimensions, and state positions for acoustic modeling

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2003, INTERSPEECH.

LIP MOVEMENT SYNTHESIS USING HMMS

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1997 .

Very low bit rate speech coding based on HMM with speaker adaptation

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2006 .

Estimating Trajectory Hmm Parameters Using Monte Carlo Em With Gibbs Sampler

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Minimum generation error training with direct log spectral distortion on LSPs for HMM-based speech synthesis

Keiichi Tokuda, Yi-Jian Wu, K. Tokuda, 2008, INTERSPEECH.

Proc. 2009 Asia-Pacific Signal and Information Processing Association (APSIPA)

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2009 .

A new algorithm for updating adaptive system

Keiichi Tokuda, Junibakti Sanubari, 2002, Asia-Pacific Conference on Circuits and Systems.

A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, IEICE Trans. Inf. Syst..

A Study on Context Clustering Techniques and Speaker Adaptive Training for Average Voice Model

Keiichi Tokuda, Takao Kobayashi, Masatsune Tamura, 2002 .

Recent development of the HMM-based speech synthesis system (HTS)

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2009 .

Continuous Speech Recognition Based on General Factor Dependent Acoustic Models(Feature Extraction and Acoustic Medelings, Corpus-Based Speech Technologies)

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005 .

Speaker interpolation in HMM-based speech synthesis system

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 1997, EUROSPEECH.

Statistical parametric speech synthesis based on product of experts

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Improvement in TF-IDF scheme for Web pages based on the contents of their hyperlinked neighboring pages

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2005 .

Decision-tree backing-off in HMM-based speech synthesis

Keiichi Tokuda, Tadashi Kitamura, Shunsuke Kataoka, 2004, INTERSPEECH.

Mmdagent—A fully open-source toolkit for voice interaction systems

Keiichi Tokuda, Akinobu Lee, Keiichiro Oura, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2009, INTERSPEECH.

A mel-cepstral analysis technique restoring high frequency components from low-sampling-rate speech

Yoshihiko Nankaku, Keiichi Tokuda, Kazuhiro Nakamura, 2014, INTERSPEECH.

Speaker recognition based on variational Bayesian method

Yoshihiko Nankaku, Keiichi Tokuda, Akinobu Lee, 2008, INTERSPEECH.

Image recognition based on discriminative models using features generated from separable lattice HMMS

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2017, 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Cross-Lingual Speaker Adaptation for HMM-Based Speech Synthesis

Keiichi Tokuda, Simon King, Yi-Jian Wu, 2008, 2008 6th International Symposium on Chinese Spoken Language Processing.

Location normalization of HMM-based lip-reading: experiments for the M2VTS database

Keiichi Tokuda, Tadashi Kitamura, Oscar Vanegas, 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

Deep neural network based real-time speech vocoder with periodic and aperiodic inputs

Yoshihiko Nankaku, Keiichi Tokuda, Kazuhiro Nakamura, 2019, 10th ISCA Workshop on Speech Synthesis (SSW 10).

Fundamental Technologies in Modern Speech Recognition [From the Guest Editors]

Keiichi Tokuda, Hermann Ney, Mark J. F. Gales, 2012 .

Low computational cost speech synthesis based on deep neural networks using hidden semi-Markov model structures

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2019 .

Voice conversion based on simultaneous modelling of spectrum and F0

Yoshihiko Nankaku, Keiichi Tokuda, Akinobu Lee, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Shinji Takaki, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM

Keiichi Tokuda, Tomoki Toda, K. Tokuda, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Probabilistic answer selection based on conditional random fields for spoken dialog system

Yoshihiko Nankaku, Keiichi Tokuda, Akinobu Lee, 2008, INTERSPEECH.

Eigenvoices for HMM-based speech synthesis

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 2002, INTERSPEECH.

An introduction of trajectory model into HMM-based speech synthesis

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2004, SSW.

Continuous Speech Recognition Based on General Factor Dependent Acoustic Models

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005, IEICE Trans. Inf. Syst..

Reformulating the HMM as a trajectory model by imposing explicit relationships between static and dynamic feature vector sequences

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2007, Comput. Speech Lang..

Statistical parametric synthesis based on products of experts

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2010 .

Speech Analysis Based on AR Model Driven by t-Distribution Process

Keiichi Tokuda, Junibakti Sanubari, M. Onoda, 1992 .

Articulatory Text-to-Speech Synthesis Using the Digital Waveguide Mesh Driven by a Deep Neural Network

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2017, INTERSPEECH.

Speaker Adaptation for Speech Synthesis Based on Deep Neural Networks Using Hidden Semi-Markov Model Structures

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, 2018 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

An HMM-Based Brazilian Portuguese Speech Synthesizer and Its Characteristics DOI: 10.14209/jcis.2006.11

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2015 .

Introduction to the Issue on Statistical Parametric Speech Synthesis

Keiichi Tokuda, Keikichi Hirose, Simon King, 2014, IEEE J. Sel. Top. Signal Process..

Speaker adaptation of pitch and spectrum for HMM-based speech synthesis

Keiichi Tokuda, Takao Kobayashi, Masatsune Tamura, 2004 .

Speaker adaptation using context clustering decision tree for HMM-based speech synthesis

Keiichi Tokuda, Takao Kobayashi, Junichi Yamagishi, 2003 .

A model structure integration based on a Bayesian framework for speech recognition

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speaker adaptation of trajectory HMMs using feature-space MLLR

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2006, INTERSPEECH.

Acoustic-to-articulatory inversion mapping with Gaussian mixture model

Keiichi Tokuda, Tomoki Toda, Alan W. Black, 2004, INTERSPEECH.

Statistical Parametric Speech Synthesis

Heiga Zen, Keiichi Tokuda, Alan W. Black, 2007, IEEE International Conference on Acoustics, Speech, and Signal Processing.

Imposture using synthetic speech against speaker verification based on spectrum and pitch

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2000, INTERSPEECH.

2-D LMA Filters -Design of Stable Two-Dimensional Digital Filters with Arbitrary Magnitude Function-

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 1992 .

Image modeling using two dimensional exponential systems

Keiichi Tokuda, Junibakti Sanubari, 1999, Proceedings 1999 International Conference on Image Processing (Cat. 99CH36348).

A very low bit rate speech coder using HMM-based speech recognition/synthesis techniques

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 1998, Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP '98 (Cat. No.98CH36181).

State Duration Modeling for HMM-Based Speech Synthesis

Heiga Zen, Keiichi Tokuda, Takao Kobayashi, 2007, IEICE Trans. Inf. Syst..

The NITech text-to-speech system for the Blizzard Challenge 2016

Keiichi Tokuda, Kei Hashimoto, Kei Sawada, 2016 .

Mapping from articulatory movements to vocal tract spectrum with Gaussian mixture model for articulatory speech synthesis

Keiichi Tokuda, Tomoki Toda, Alan W. Black, 2004, SSW.

Stereo-based stochastic noise compensation based on trajectory GMMS

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Generalization of Thai tone contour in HMM-based speech synthesis

Keiichi Tokuda, Keiichiro Oura, Anocha Rugchatjaroen, 2017, 2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Performance evaluation of the speaker-independent HMM-based speech synthesis system “HTS 2007” for the Blizzard Challenge 2007

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Separable lattice 2-D HMMS introducing state duration control for recognition of images with various variations

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

The blizzard machine learning challenge 2017

Keiichi Tokuda, Simon King, Alan W. Black, 2017, 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Incorporating a mixed excitation model and postfilter into HMM-based text-to-speech synthesis

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 2005, Systems and Computers in Japan.

Image recognition based on hidden Markov eigen-image models using variational Bayesian method

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2013, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.

Adaptive cepstral analysis of speech

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 1995, IEEE Trans. Speech Audio Process..

Speaker adaptation based on nonlinear spectral transform for speech recognition

Yoshihiko Nankaku, Keiichi Tokuda, Akinobu Lee, 2010, INTERSPEECH.

The effect of neural networks in statistical parametric speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-Space Probability Distribution HMM

Keiichi Tokuda, Takashi Masuko, Noboru Miyazaki, 2002 .

Adaptation of pitch and spectrum for HMM-based speech synthesis using MLLR

Keiichi Tokuda, Takao Kobayashi, Masatsune Tamura, 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

A SPEECH PARAMETER GENERATION ALGORITHM BASED ON HMM

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1996 .

Pitch pattern generation using multispace probability distribution HMM

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2002, Systems and Computers in Japan.

Visual Speech Synthesis Based on Parameter Generation From HMM: Speech-Driven and Text-And-Speech-Driven Approaches

Keiichi Tokuda, Takao Kobayashi, Masatsune Tamura, 1998, AVSP.

Very low bit rate speech coding based on HMMs

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 2001, Systems and Computers in Japan.

Audio-visual speech recognition using MCE-based hmms and model-dependent stream weights

Keiichi Tokuda, Tadashi Kitamura, Chiyomi Miyajima, 2000, INTERSPEECH.

Decision tree distribution tying based on a dimensional split technique

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2002, INTERSPEECH.

Simultaneous modeling of spectrum, pitch and duration in HMM-based speech synthesis

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 1999, EUROSPEECH.

State mapping based method for cross-lingual speaker adaptation in HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Yi-Jian Wu, 2009, INTERSPEECH.

On the Use of Kernel PCA for Feature Extraction in Speech Recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2003, IEICE Trans. Inf. Syst..

Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model

Keiichi Tokuda, Tomoki Toda, Alan W. Black, 2008, Speech Commun..

Contextual Additive Structure for HMM-Based Speech Synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Shinji Takaki, 2014, IEEE Journal of Selected Topics in Signal Processing.

Acoustic modeling with contextual additive structure for HMM-based speech recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Towards the development of a brazilian portuguese text-to-speech system based on HMM

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2003, INTERSPEECH.

Normalized training for HMM‐Based visual speech recognition

Yoshihiko Nankaku, Keiichi Tokuda, Takao Kobayashi, 2006 .

The Nitech-NAIST HMM-Based Speech Synthesis System for the Blizzard Challenge 2006

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2008, IEICE Trans. Inf. Syst..

Lip Location Normalized Training for Visual Speech Recognition

Keiichi Tokuda, Tadashi Kitamura, Oscar Vanegas, 2000 .

Constructing text-to-speech systems for languages with unknown pronunciations

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018 .

3. Multi-language Speech Synthesis

Keiichi Tokuda, Hisashi Kawai, 2010 .

Text-to-speech synthesis with arbitrary speaker's voice from average voice

Keiichi Tokuda, Takao Kobayashi, Masatsune Tamura, 2001, INTERSPEECH.

INVITED PAPER Special Issue on the 2000 IEICE Excellent Paper Award Multi-Space Probability Distribution HMM ∗∗

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2002 .

Contextual partial additive structure for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Shinji Takaki, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

A trainable excitation model for HMM-based speech synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2007, INTERSPEECH.

Product of Experts for Statistical Parametric Speech Synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2012, IEEE Transactions on Audio, Speech, and Language Processing.

Singing Voice Synthesis Based on Generative Adversarial Networks

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

On the security of HMM-based speaker verification systems against imposture using synthetic speech

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1999, EUROSPEECH.

The HMM-basedSpeechSynthesisSystem(HTS)Version2.0

Keiichi Tokuda, Junichi Yamagishi, Universityof Edinburgh, 2007 .

Speech parameter generation algorithms for HMM-based speech synthesis

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 2000, 2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).

Design of stable two-dimensional IIR digital filters with arbitrary magnitude function

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 1992, [Proceedings] ICASSP-92: 1992 IEEE International Conference on Acoustics, Speech, and Signal Processing.

HMM compensation for noisy speech recognition based on cepstral parameter generation

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1997, EUROSPEECH.

Parameter sharing and minimum classification error training of mixtures of factor analyzers for speaker identification

Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Hidden Markov models based on multi-space probability distribution for pitch pattern modeling

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1999, 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No.99CH36258).

Simultaneous Optimization of Multiple Tree-Based Factor Analyzed HMM for Speech Synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2017, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Full covariance state duration modeling for HMM-based speech synthesis

Keiichi Tokuda, Li-Rong Dai, Ren-Hua Wang, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Face recognition based on separate lattice HMMs

Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, 2006 .

Constructing emotional speech synthesizers with limited speech database

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2004, INTERSPEECH.

Cross-lingual speaker adaptation for HMM-based speech synthesis considering differences between language-dependent average voices

Yoshihiko Nankaku, Keiichi Tokuda, Keiichiro Oura, 2010 .

Applying Sparse KPCA for Feature Extraction in Speech Recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2005, IEICE Trans. Inf. Syst..

Pixel-based Lip Movement Synthesis using HMMs

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 1999 .

Sentence generation from keywords using N-gram for Spoken Dialog System

Yoshihiko Nankaku, Keiichi Tokuda, Akinobu Lee, 2009 .

Image Recognition Based on Separable Lattice Hmms Using a Deep Neural Network for Output Probability Distributions

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Mixed excitation for HMM-based speech synthesis

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 2001, INTERSPEECH.

Generalized cepstral analysis of speech - unified approach to LPC and cepstral method

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 1990, ICSLP.

Parameter Sharing in Mixture of Factor Analyzers for Speaker Identification

Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, 2005, IEICE Trans. Inf. Syst..

Bayesian Context Clustering Using Cross Validation for Speech Recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2011, IEICE Trans. Inf. Syst..

Audio-visual speech recognition using minimum classification error training

Keiichi Tokuda, Tadashi Kitamura, Chiyomi Miyajima, 2000, Neural Networks for Signal Processing X. Proceedings of the 2000 IEEE Signal Processing Society Workshop (Cat. No.00TH8501).

A VERY LOW SPEECH CODER U IHEMfiI-BASED SPEECH GNITION/SYNTMESIS

Keiichi Tokuda, Takashi Masuko, Jun Hiroi, 1998 .

An HMM-Based Approach to Flexible Speech Synthesis

Keiichi Tokuda, 2006, ISCSLP.

Bayesian context clustering using cross valid prior distribution for HMM-based speech recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, INTERSPEECH.

Minimum classification error interactive training for speaker identification [interactive robot applications]

Keiichi Tokuda, Tadashi Kitamura, Yusuke Kida, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

A Reordering Model Using a Source-Side Parse-Tree for Statistical Machine Translation

Keiichi Tokuda, Eiichiro Sumita, Hirofumi Yamamoto, 2009, IEICE Trans. Inf. Syst..

A New Robust Two Dimensional Spectral Estimation Based on an AR Model Excited by a t Distribution Process and its QR-Decomposition Recursive Algorithm

Keiichi Tokuda, Junibakti Sanubari, 1999, J. Circuits Syst. Comput..

Fundamental Technologies in Modern Speech Recognition

Keiichi Tokuda, Hermann Ney, Mark J. F. Gales, 2012 .

RLS-type two-dimensional adaptive filter with a t-distribution assumption

Keiichi Tokuda, Junibakti Sanubari, 2000, Signal Process..

Deterministic annealing based training algorithm for Bayesian speech recognition

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2009, INTERSPEECH.

A Study on Discrimination between Synthetic and Natural Speech for Speaker Verification Systems

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2001 .

Face Recognition Based on Separable Lattice HMMS

Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

A very low bit rate speech coder using HMM with speaker adaptation

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1998, ICSLP.

HMM-based visual speech recognition using intensity and location normalization

Keiichi Tokuda, Tadashi Kitamura, Oscar Vanegas, 1998, ICSLP.

On the state definition for a trainable excitation model in HMM-based speech synthesis

Keiichi Tokuda, Tomoki Toda, Ranniery Maia, 2008, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing.

Prediction Method of Speech Recognition Performance Based on HMM-based Speech Synthesis Technique

Keiichi Tokuda, Tadashi Kitamura, Toshihiro Wakita, 2010 .

CELP coding system based on mel-generalized cepstral analysis

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

Singing voice synthesis based on convolutional neural networks pdf

Yoshihiko Nankaku, Keiichi Tokuda, Kazuhiro Nakamura, 2019, ArXiv.

A Bayesian Framework Using Multiple Model Structures for Speech Recognition

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2013, IEICE Trans. Inf. Syst..

Simultaneous conversion of duration and spectrum based on statistical models including time-sequence matching

Yoshihiko Nankaku, Keiichi Tokuda, Tomoki Toda, 2008, INTERSPEECH.

Temporal modeling in neural network based statistical parametric speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2016, SSW.

Robust estimation of an AR multi-channel model by using t-distribution assumption

Keiichi Tokuda, Junibakti Sanubari, 2000, 2000 10th European Signal Processing Conference.

Intensity- and location-normalized training for HMM-based visual speech recognition

Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, 1999, EUROSPEECH.

Very low bit rate speech coding based on HMM with speaker adaptation

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2006, Systems and Computers in Japan.

"Developing a Test Bed of English Text-to-Speech System XIMERA for the Blizzard Challenge 2006 for the Blizzard Challenge 2006"

Keiichi Tokuda, Tomoki Toda, Satoshi Nakamura, 2006 .

Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis

Keiichi Tokuda, Simon King, Junichi Yamagishi, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Realizing Tibetan speech synthesis by speaker adaptive training

Keiichi Tokuda, Zhenye Gan, Hongwu Yang, 2013, 2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference.

On the Use of Phonetic Information for Mapping from Articulatory Movements to Vocal Tract Spectrum

Yoshihiko Nankaku, Keiichi Tokuda, Tomoki Toda, 2006, 2006 IEEE International Conference on Acoustics Speech and Signal Processing Proceedings.

Speech Synthesis Based on Hidden Markov Models

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2013, Proceedings of the IEEE.

HMM‐based speech synthesis with various voice characteristics

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1996 .

A Bayesian approach to HMM-based speech synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Large-Scale Subjective Evaluations of Speech Rate Control Methods for HMM-Based Speech Synthesizers

Keiichi Tokuda, Makoto Yamada, Tsuneo Kato, 2011, INTERSPEECH.

The training algorithm based on variational approximation for separable 2D-HMM

Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, 2003 .

A Speech Parameter Generation Algorithm Considering Global Variance for HMM-Based Speech Synthesis

Keiichi Tokuda, Tomoki Toda, K. Tokuda, 2007, IEICE Trans. Inf. Syst..

Integration of speaker and pitch adaptive training for HMM-based singing voice synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Keiichiro Oura, 2014, 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

A Bayesian Approach to Speaker Recognition Based on GMMs Using Multiple Model Structures

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2012, INTERSPEECH.

The NICT/ATR speech synthesis system for the Blizzard Challenge 2008

Keiichi Tokuda, Tomoki Toda, Satoshi Nakamura, 2008 .

Recent advances in statistical parametric speech synthesis

Keiichi Tokuda, K. Tokuda, 2010 .

Vector quantization of mel-cepstral coefficients using distortion measure for spectral analysis

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 2007, Systems and Computers in Japan.

Mel-generalized cepstral analysis - a unified approach to speech spectral estimation

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1994, ICSLP.

An excitation model for HMM-based speech synthesis based on residual modeling

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2007, SSW.

GMM-Based Missing-Feature Reconstruction on Multi-Frame Windows

Yoshihiko Nankaku, Keiichi Tokuda, Ulpu Remes, 2011, INTERSPEECH.

An extension of Separable Lattice 2-D HMMS for rotational data variations

Yoshihiko Nankaku, Keiichi Tokuda, Akira Tamamori, 2010, 2010 IEEE International Conference on Acoustics, Speech and Signal Processing.

Face recognition based on separable lattice 2-D HMMS using variational bayesian method

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2012, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

CELP speech coding based on mel‐generalized cepstral analyses

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 2000 .

Probabilistic feature mapping based on trajectory HMMs

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, INTERSPEECH.

Special Section on Corpus-Based Speech Technologies

Keiichi Tokuda, Kiyohiro Shikano, Koichi Shinoda, 2005 .

Minimum generation error training by using original spectrum as reference for log spectral distortion measure

Keiichi Tokuda, Yi-Jian Wu, K. Tokuda, 2009, 2009 IEEE International Conference on Acoustics, Speech and Signal Processing.

Personalising speech-to-speech translation: Unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis

Keiichi Tokuda, Mikko Kurimo, William J. Byrne, 2013, Comput. Speech Lang..

The HTS-2008 System: Yet Another Evaluation of the Speaker-Adaptive HMM-based Speech Synthesis System in The 2008 Blizzard Challenge

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2008 .

Simultaneous clustering of phonetic context, dimension, and state position for acoustic modeling using decision trees

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2005, Systems and Computers in Japan.

Spectral modeling with contextual additive structure for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Shinji Takaki, 2010, SSW.

Efficient encoding of mel-generalized cepstrum for CELP coders

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 1997, 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing.

Pitch adaptive training for hmm-based singing voice synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Kazuhiro Nakamura, 2014, 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speaker-Independent HMM-based Speech Synthesis System

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2007 .

Speech recognition using voice-characteristic-dependent acoustic models

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2003, 2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03)..

Acoustic modeling based on model structure annealing for speech recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2008, INTERSPEECH.

Speaker adaptation for HMM-based speech synthesis system using MLLR

Keiichi Tokuda, Takao Kobayashi, Masatsune Tamura, 1998, SSW.

Robust Speaker-Adaptive HMM-Based Text-to-Speech Synthesis

Heiga Zen, Keiichi Tokuda, Tomoki Toda, 2009, IEEE Transactions on Audio, Speech, and Language Processing.

A 16 kbit/s wideband CELP coder using MEL-generalized cepstral analysis and its subjective evaluation

Keiichi Tokuda, Takao Kobayashi, Kazuhito Koishida, 1998, ICSLP.

A Bayesian Approach to Voice Conversion Based on GMMs Using Multiple Model Structures

Yoshihiko Nankaku, Keiichi Tokuda, Lei Li, 2011, INTERSPEECH.

Reordering Model Using Syntactic Information of a Source Tree for Statistical Machine Translation

Keiichi Tokuda, Eiichiro Sumita, Kei Hashimoto, 2009, SSST@HLT-NAACL.

Robust recursive time series modeling based on an AR model excited by a t-distribution process

Keiichi Tokuda, Junibakti Sanubari, Mahoki Onoda, 1998, IEEE Trans. Signal Process..

A Covariance-Tying Technique for HMM-Based Speech Synthesis

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2010, IEICE Trans. Inf. Syst..

The HMM-based speech synthesis system (HTS) version 2.0

Heiga Zen, Keiichi Tokuda, Takashi Nose, 2007, SSW.

A Study on Phoneme Models for Speech Synsesis Using HMMs.

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1996 .

Statistical Voice Conversion Based on Wavenet

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

WaveNet-Based Zero-Delay Lossless Speech Coding

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2018, 2018 IEEE Spoken Language Technology Workshop (SLT).

Vector Quantization of Speech Spectral Parameters Using Statistics of Static and Dynamic Features

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 2001 .

Reformulating the HMM as a Trajectory Model

Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, 2004 .

Fast and High-Quality Singing Voice Synthesis System Based on Convolutional Neural Networks

Yoshihiko Nankaku, Keiichi Tokuda, Kazuhiro Nakamura, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech recognition based on statistical models including multiple phonetic decision trees

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2011 .

Noisy environment adaptation of HMM using ML parameter generation.

Keiichi Tokuda, Takao Kobayashi, Takashi Masuko, 1996 .

An analysis of machine translation and speech synthesis in speech-to-speech translation system

Keiichi Tokuda, William J. Byrne, Simon King, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Question Answering based on Automatic Utterance Clustering in Spoken Dialogue System

Yoshihiko Nankaku, Keiichi Tokuda, Akinobu Lee, 2007 .

Global variance modeling on frequency domain delta LSP for HMM-based speech synthesis

Yoshihiko Nankaku, Keiichi Tokuda, Jianhua Tao, 2011, 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Hidden semi-Markov model based speech synthesis

Heiga Zen, Keiichi Tokuda, Takao Kobayashi, 2004, INTERSPEECH.

Voice Conversion Based on Trajectory Model Training of Neural Networks Considering Global Variance

Yoshihiko Nankaku, Keiichi Tokuda, Naoki Hosaka, 2016, INTERSPEECH.

A Frame-Based Context-Dependent Acoustic Modeling for Speech Recognition

Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, 2010 .

An improved minimum generation error based model adaptation for HMM-based speech synthesis

Keiichi Tokuda, Long Qin, Yi-Jian Wu, 2009, INTERSPEECH.

Voice activity detection based on conditional random fields using multiple features

Yoshihiko Nankaku, Keiichi Tokuda, Akira Saito, 2010, INTERSPEECH.

Simultaneous Acoustic, Prosodic, and Phrasing Model Training for TTs Conversion Systems

Yoshihiko Nankaku, Keiichi Tokuda, Tomoki Toda, 2008, 2008 6th International Symposium on Chinese Spoken Language Processing.

Analysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using KLD-based transform mapping

Keiichi Tokuda, Simon King, Junichi Yamagishi, 2012, Speech Commun..

Speech coding based on adaptive mel‐cepstral analysis and its evaluation

Keiichi Tokuda, Takao Kobayashi, Satoshi Imai, 1995 .

HMM-based text-to-audio-visual speech synthesis

Keiichi Tokuda, Takao Kobayashi, Tadashi Kitamura, 2000, INTERSPEECH.

Unsupervised English-to-Japanese speaker adaptation for HMM-based speech synthesis.

Keiichi Tokuda, Simon King, Junichi Yamagishi, 2009 .

A new approach to designing a feature extractor in speaker identification based on discriminative feature extraction

Keiichi Tokuda, Shigeru Katagiri, Tadashi Kitamura, 2001, Speech Commun..

Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2021, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

PeriodNet: A Non-Autoregressive Raw Waveform Generative Model With a Structure Separating Periodic and Aperiodic Components

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2021, IEEE Access.

Neural Sequence-to-Sequence Speech Synthesis Using a Hidden Semi-Markov Model Based Structured Attention Mechanism

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2021, 2108.13985.

Periodnet: A Non-Autoregressive Waveform Generation Model with a Structure Separating Periodic and Aperiodic Components

Yoshihiko Nankaku, Keiichi Tokuda, Kei Hashimoto, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Spectral quantization using statistics of static and dynamic features

Keiichi Tokuda, Kazuhito Koishida, Takashi Masuko, 1997, 1997 IEEE Workshop on Speech Coding for Telecommunications Proceedings. Back to Basics: Attacking Fundamental Problems in Speech Coding.

Spectral representation of speech using mel‐generalized cepstral coefficients

Keiichi Tokuda, Satoshi Imai, Kazuhito Koishida, 1996 .

RLS algorithms for adaptive AR spectrum analysis based on multi-band decomposition of the linear prediction error

Keiichi Tokuda, Akinori Nishihara, Mineo Kaneko, 1996, Proceedings of Digital Processing Applications (TENCON '96).

Recursive Calculation of Mel-Cepstrum from LP Coefficients

Keiichi Tokuda, Satoshi Imai, Takao Kobayashi, 1994 .

New adaptive algorithms based on multi-band decomposition of the error signal

Keiichi Tokuda, Akinori Nishihara, Paulo S. R. Diniz, 1998 .

Quantization of vector sequences using statistics of neighboring input vectors

Keiichi Tokuda, Satoshi Imai, Takashi Masuko, 1996 .

Spectral representation of speech based on mel‐generalized cepstral coefficients and its properties

Keiichi Tokuda, Satoshi Imai, Kazuhito Koishida, 2000 .

Noisy speech recognition using HMM‐based cepstral parameter generation and compensation

Keiichi Tokuda, Satoshi Imai, Takashi Masuko, 1996 .