TOKUDA Keiichi

写真a

Affiliation Department etc.

Department of Computer Science
Department of Computer Science

Title

Professor

Graduating School

  •  
    -
    1984.03

    Nagoya Institute of Technology   Faculty of Engineering   Graduated

Graduate School

  •  
    -
    1989.03

    Tokyo Institute of Technology  Graduate School, Division of Integrated Science and Engineering  Doctor's Course  Completed

Degree

  • Tokyo Institute of Technology -  Master of Engineering

  • Tokyo Institute of Technology -  Doctor of Engineering

External Career

  • 1989.04
    -
    1996.03

    Tokyo Institute of Technology   Research Assistant  

Academic Society Affiliations

  •  
     
     

    ISCA

  • 2000.04
    -
    Now

    IEEE(The Institute of Electrical and Electronics Engineers)

Field of expertise (Grants-in-aid for Scientific Research classification)

  • Perceptual information processing

 

Research Career

  • Speech Recognition

    (not selected)  

    Project Year:   - 

  • Speech Synthesis

    (not selected)  

    Project Year:   - 

  • Multimedia Signal Processing

    (not selected)  

    Project Year:   - 

Papers

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

    Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    IEEE Access   9   137599 - 137612   2021.10  [Refereed]

    Research paper (scientific journal)   Multiple Authorship

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

    Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    IEEE/ACM Transactions on Audio, Speech and Language Processing   29   2803 - 2815   2021.08  [Refereed]

    Research paper (scientific journal)   Multiple Authorship

  • PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components

    Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    Proceedings of 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021)     6049 - 6053   2021.06  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • Hierarchical multi-grained generative model for expressive speech synthesis

    Yukiya Hono, Kazuna Tsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku and Keiichi Tokuda

    Interspeech2020 Proceedings     2020.10  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • Semi-supervised learning based on hierarchical generative models for end-to-end speech synthesis

    Takato Fujimoto, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

    2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)     7644 - 7648   2020.05  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • Fast and high-quality singing voice synthesis system based on convolutional neural networks

    Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda

    2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)     7239 - 7243   2020.05  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • A vector quantized variational autoencoder (VQ-VAE) autoregressive neural F0 model for statistical parametric speech synthesis

    Xin Wang, Shinji Takaki, Junichi Yamagishi, Simon King, and Keiichi Tokuda

    IEEE/ACM Transactions on Audio, Speech, and Language Processing ( IEEE )  28   157 - 170   2019.11  [Refereed]

    Research paper (scientific journal)   Multiple Authorship

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

    Keiichiro Oura, Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    10th ISCA Speech Synthesis Workshop (SSW10)     2019.09  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

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

    Takato Fujimoto, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    10th ISCA Speech Synthesis Workshop (SSW10)     2019.09  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

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

    Motoki Shimada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    10th ISCA Speech Synthesis Workshop (SSW10)     2019.09  [Refereed]

    Research paper (bulletin of university, research institution)   Multiple Authorship

display all >>

Books

  • Human Harmonized Information Technology, Volume 2

    Keiichi Tokuda, Akinobu Lee, Yoshihiko Nankaku, Keiichiro Oura, Kei Hashimoto, Daisuke Yamamoto, Ichi Takumi, Takahiro Uchiya, Shuhei Tsutsumi, Steve Renals, and Junichi Yamagishi (Part: Multiple Authorship ,  User generated dialogue systems: uDialogue )

    Springer  2017.05 ISBN: 978-4-431-56533-8

  • Resources and Standards of Spoken Language Systems --Advances in Oriental Spoken Language Processing--

    (Part: Multiple Authorship )

    World Scientific Publishing Co.  2009.04

  • An HMM-Based Approach to Multilingual Speech Synthesis

    (Part: Single Author )

    Prentice Hall  2004.04

  • Galatea: Open-source Software for Developing Anthropomorphic Spoken Dialog Agents

    (Part: Single Author )

    Springer-Verlag  2004.04

Presentations

  • PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components

    Yukiya Hono, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    2021 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2021)  2021.06  -  2021.06 

  • Hierarchical multi-grained generative model for expressive speech synthesis

    Yukiya Hono, Kazuna Tsuboi, Kei Sawada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku and Keiichi Tokuda

    INTERSPEECH 2020  (オンライン)  2020.10  -  2020.10  ISCA

  • Semi-supervised learning based on hierarchical generative models for end-to-end speech synthesis

    Takato Fujimoto, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  (Barcelona, Spain)  2020.05  -  2020.05  IEEE

  • Fast and high-quality singing voice synthesis system based on convolutional neural networks

    Takato Fujimoto, Shinji Takaki, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  (Barcelona, Spain)  2020.05  -  2020.05  IEEE

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

    Keiichiro Oura, Kazuhiro Nakamura, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda

    10th ISCA Speech Synthesis Workshop (SSW10)  (Vienne, Austria)  2019.09  -  2019.09  ISCA

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

    Motoki Shimada, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    10th ISCA Speech Synthesis Workshop (SSW10)  (Vienne, Austria)  2019.09  -  2019.09  ISCA

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

    Takato Fujimoto, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    10th ISCA Speech Synthesis Workshop (SSW10)  (Vienne, Austria)  2019.09  -  2019.09  ISCA

  • Statistical Approach to Speech Synthesis: Past, Present and Future

    Keiichi Tokuda  [Invited]

    Interspeech 2019  (Messecongress Graz)  2019.09  -  2019.09  ISCA

  • Singing voice synthesis based on generative adversarial networks

    Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019)  (Brighton, UK)  2019.05  -  2019.05  IEEE

  • Speaker-dependent WaveNet-based delay-free ADPCM speech coding

    Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda

    2019 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2019)  (Brighton, UK)  2019.05  -  2019.05  IEEE

display all >>

Other research activities

  • Open JTalk-1.00

    2009.04  -  2009.04

  • Flite+hts_engine-1.00

    2009.04  -  2009.04

  • hts_engine API-1.02

    2009.04  -  2009.04

  • SPTK-3.3

    2009.04  -  2009.04

  • Julius-4.1.4

    2009.04  -  2009.04

Academic Awards Received

  • 2009 IEEE Signal Processing Society ``Young Author Best Paper Award''

    2010.03    

  • the TELECOM System Technology Prize from the Telecommunications Advancement Foundation Award

    2001.04    

  • the Excellent Paper Award of IEICE

    2001.04    

  • the Inose Award of IEICE

    2001.04