Keiichi Tokuda
Professor Emeritus / Visiting Professor
Nagoya Institute of Technology
Keiichi Tokuda is a researcher in speech synthesis, speech signal processing, and statistical machine learning. His work has contributed to statistical parametric speech synthesis, HMM-based speech synthesis, neural speech synthesis, singing voice synthesis, voice conversion, and related speech technologies.
He served as a professor at Nagoya Institute of Technology until March 2026. He is currently Professor Emeritus and Visiting Professor at Nagoya Institute of Technology.
I also share the latest news and updates on X (formerly Twitter). Sorry, it is mostly in Japanese.
Work History
- 1989–1996 Tokyo Institute of Technology (now Institute of Science Tokyo)
- 1996–present Nagoya Institute of Technology
Sabbatical
- 2001–2002 Carnegie Mellon University
- 2014–2015 Google, London
Part time
- April 2006–March 2013 Visiting Researcher, National Institute of Information and Communications Technology (NiCT), Japan
- April 2002–March 2006 Visiting Researcher, ATR Spoken Language Communication Laboratories, Japan
- July 2001–April 2002 Visiting Researcher, Language Technologies Institute Carnegie Mellon University
- April 2001–September 2001 Invited Lecturer, Nagoya University, Japan
- August 2000–July 2001 Visiting Researcher, ATR Spoken Language Translation Laboratories, Japan
- November 1997–March 1998 Invited Lecturer, Tokyo Institute of Technology, Japan
Awards
- 2024 IEEE James L. Flanagan Speech and Audio Processing Award link
- 2020 The Medal with Purple Ribbon, Government of Japan
- 2019 ISCA Best Paper Award, 6th ISCA Speech Synthesis Workshop
- 2019 ISCA Medal for Scientific Achievement link
- 2015 Achievement Award from the Institute of Electronics, Information and Communication Engineers
- 2013 IPSJ Kiyasu Special Industrial Achievement Award (Information Processing Society of Japan)
- 2013 The 2013 EURASIP-ISCA Best Paper Award (Speech Communication Journal)
- 2012 Prizes for Science and Technology (Research Category), The Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology
- 2008 Information and Systems Society Distinguished Achievement Award from the Institute of Electronics, Information and Communication Engineers
- 2008 Information and Systems Society Excellent Paper Award from the Institute of Electronics, Information and Communication Engineers
- 2008 TELECOM System Technology Prize from the Telecommunications Advancement Foundation
- 2001 Best Paper Award from the Institute of Electronics, Information and Communication Engineers
- 2001 Inose Award (the highest award) from the Institute of Electronics, Information and Communication Engineers
- 2001 TELECOM System Technology Prize from the Telecommunications Advancement Foundation
Fellowships and Professional Honors
- IEEE Fellow
- ISCA Fellow
- AAIA Fellow
- Sigma Xi Full Member
- Honorary Professor at the University of Edinburgh (2012–2017)
Software & Resources
- HTS A software toolkit for HMM/DNN-based speech synthesis.
- SPTK A suite of tools for speech analysis, parameter conversion, synthesis filtering, and related speech signal processing tasks.
The newer SPTK 4.0+ and the differentiable PyTorch-based diffsptk are also available. These recent versions have been developed in my research group. I have been involved in the research direction, while the software design and implementation have been led mainly by Takenori Yoshimura. - hts_engine API A speech synthesis engine API for generating speech waveforms from models trained by HTS.
- Open JTalk A Japanese text-to-speech system based on HTS technology.
- Sinsy A singing voice synthesis system that generates singing voices from musical scores.
- MMDAgent A toolkit for building voice interaction systems using CG characters.
Its successor, MMDAgent-EX, is currently developed and maintained separately by Prof. Akinobu Lee.
Please refer to each project page for the latest information, documentation, and usage conditions.
Links
Contact
Email: tokuda [at] nitech.ac.jp