|
Affiliation Department etc. |
Department of Computer Science
|
|
Title |
Professor |
TOKUDA Keiichi
|
|
|
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
-
The NITech text-to-speech system for the Blizzard Challenge 2016
Kei Sawada, Chiaki Asai, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda
Blizzard Challenge 2016 Workshop 2016.09 [Refereed]
Research paper (international conference proceedings) Multiple Authorship
-
Temporal modeling in neural network based statistical parametric speech synthesis
Keiichi Tokuda, Kei Hashimoto, Keiichiro Oura, and Yoshihiko Nankaku
9th ISCA Speech Synthesis Workshop 113 - 118 2016.09 [Refereed]
Research paper (international conference proceedings) Multiple Authorship
-
Singing voice synthesis based on deep neural networks
Masanari Nishimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Interspeech 2016 2478 - 2482 2016.09 [Refereed]
Research paper (international conference proceedings) Multiple Authorship
-
Redefining the linguistic context feature set for HMM and DNN TTS through position and parsing
Rasmus Dall, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Interspeech 2016 2851 - 2855 2016.09 [Refereed]
Research paper (international conference proceedings) Multiple Authorship
-
Voice conversion based on trajectory model training of neural networks considering global variance
Naoki Hosaka, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Interspeech 2016 307 - 311 2016.09 [Refereed]
Research paper (international conference proceedings) Multiple Authorship
-
A hierarchical predictor of synthetic speech naturalness using neural networks
Takenori Yoshimura, Gustav Eje Henter, Oliver Watts, Mirjam Wester, Junichi Yamagishi, and Keiichi Tokuda
Interspeech 2016 342 - 346 2016.09 [Refereed]
Research paper (international conference proceedings) Multiple Authorship
-
Image recognition based on discriminative models using features extracted from separable lattice HMMs
116 ( 89 ) 7 - 12 2016.06
Research paper (research society, symposium materials, etc.) Multiple Authorship
-
Directly modeling voiced and unvoiced components in speech waveforms by neural networks
Keiichi Tokuda, and Heiga Zen
2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 5640 - 5644 2016.03 [Refereed]
Research paper (international conference proceedings) Multiple Authorship
-
Trajectory training considering global variance for speech synthesis based on neural networks
Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 5600 - 5604 2016.03 [Refereed]
Research paper (international conference proceedings) Multiple Authorship
-
Investigation of voice fundamental frequency estimation based on conditional random fields
279 - 280 2016.03
Research paper (other science council materials etc.) Multiple Authorship
Books
-
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
-
The NITech text-to-speech system for the Blizzard Challenge 2016
Kei Sawada, Chiaki Asai, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda
Blizzard Challenge 2016 Workshop 2016.09 - 2016.09
-
Temporal modeling in neural network based statistical parametric speech synthesis
Keiichi Tokuda, Kei Hashimoto, Keiichiro Oura, and Yoshihiko Nankaku
9th ISCA Speech Synthesis Workshop 2016.09 - 2016.09
-
Voice conversion based on trajectory model training of neural networks considering global variance
Naoki Hosaka, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Interspeech 2016 2016.09 - 2016.09
-
Redefining the linguistic context feature set for HMM and DNN TTS through position and parsing
Rasmus Dall, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Interspeech 2016 2016.09 - 2016.09
-
Singing voice synthesis based on deep neural networks
Masanari Nishimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
Interspeech 2016 2016.09 - 2016.09
-
A hierarchical predictor of synthetic speech naturalness using neural networks
Takenori Yoshimura, Gustav Eje Henter, Oliver Watts, Mirjam Wester, Junichi Yamagishi, and Keiichi Tokuda
Interspeech 2016 2016.09 - 2016.09
-
Directly modeling voiced and unvoiced components in speech waveforms by neural networks
Keiichi Tokuda, and Heiga Zen
2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (Shanghai, China) 2016.03 - 2016.03 IEEE
-
Trajectory training considering global variance for speech synthesis based on neural networks
Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda
2016 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (Shanghai, China) 2016.03 - 2016.03 IEEE
-
Text-to-speech Synthesis as a Machine Learning Problem
Keiichi Tokuda [Invited]
Recent Advances in Machine Learning and Applications (Aichi) 2015.11 - 2015.11
-
The NITECH HMM-based text-to-speech system for the Blizzard Challenge 2015
Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda
Blizzard Challenge 2015 Workshop (Berlin, Germany) 2015.09 - 2015.09
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 Inose Award of IEICE
2001.04
-
the TELECOM System Technology Prize from the Telecommunications Advancement Foundation Award
2001.04
-
the Excellent Paper Award of IEICE
2001.04