ENGLISH PAGE (JAPANESE PAGE)
Tokuda & Lee Laboratory
Tokuda & Lee Laboratory/Oura Keiichiro
Tokuda & Lee Laboratory/Oura Keiichiro/research (private page)
Name †
Nagoya Institute of Technology, Assistant Professor
- First name
Keiichiro
- Family name
Oura
Society †
- Acoustical Society of Japan
- Information Processing Society of Japan
Contact infomation †
- Address
Department of Computer Science and Engineering, Nagoya Institute of Technology, Gokiso-cho, Showa-ku, Nagoya, 466-8555 Japan
- TEL/FAX
81-52-735-7549/5840
- E-Mail
uratec@nitech.ac.jp
Please, *do not* ask any questions about software (or algorithm) to me *directly*. Use the mailing lists. I don't answer to you.
Biography †
- Professional Experiences
- Educations
- Apr. 2007 - Mar. 2010
Nagoya Institute of Technology, Department of Computer Science and Engineering (Ph.D.)
- Apr. 2005 - Mar. 2007
Nagoya Institute of Technology, Department of Computer Science and Engineering (Master)
- Apr. 2001 - Mar. 2005
Nagoya Institute of Technology, Department of Computer Science
- Awards
- Mar. 2012
IPSJ Yamashita SIG Research Award
- Feb. 2010
Student Award at Nagoya Institute of Technology
- Dec. 2008
Best Student Paper Award at ISCSLP2008
Software †
Main Member †
- HTS
HMM-based speech synthesis system (Design and Development, Main Maintainer).
- hts_engine API
Speech synthesis engine for HTS (Design and Development, Main Maintainer).
- SPTK
Speech signal processing toolkit (Main Maintainer).
- MMDAgent
Toolkit for building voice interaction systems (Project Member).
- Sinsy
HMM-based singing voice synthesis system (Project Member).
Sub Member †
- Festival
Language-independent TTS system (Developer of HMM-based speech synthesis module).
Work †
- SPECOM (2012)
Analysis of unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis using KLD-based transform mapping,
Keiichiro Oura, Junichi Yamagishi, Mirjam Wester, Simon King, and Keiichi Tokuda,
Speech Communication, 2012 (accepted).
- CSL (2012)
Personalising speech-to-speech translation: unsupervised cross-lingual speaker adaptation for HMM-based speech synthesis,
John Dines, Hui Liang, Matthew Gibson, Keiichiro Oura, Junichi Yamagishi, Simon King, Mirjam Wester, Lakshmi Saheer, Teemu Hirsimaki, Reima Karhila, Keiichi Tokuda, William Byrne, and Mikko Kurimo,
Computer Speech and Language, 2012 (accepted).
- ICASSP2012 in Kyoto, Japan (Mar. 25-30 2012)
Pitch adaptive training for HMM-based singing voice synthesis,
Keiichiro Oura, Ayami Mase, Yoshihiko Nankaku, and Keiichi Tokuda,
ICASSP 2012, 2012-03 (accepted).
- SIGMUS2012 in Hamamatsu, Japan (Feb. 03-04 2012)
HMM-based synthesis of singing voices using pitch adaptive training,
Keiichiro Oura, Ayami Mase, Yoshihiko Nankaku, and Keiichi Tokuda,
Technical Report of IPSJ, 2012-02.
- SIGMUS2012 in Hamamatsu, Japan (Feb. 03-04 2012)
Rap-style singing voice synthesis,
Keijiro Saino, Keiichiro Oura, Makoto Tachibana, Hideki Kenmochi, and Keiichi Tokuda,
Technical Report of IPSJ, 2012-02.
- SIGMUS2012 in Hamamatsu, Japan (Feb. 03-04 2012)
Sinsy - human-like singing system based on automatic learning,
Keiichi Tokuda, and Keiichiro Oura,
Technical Report of IPSJ, 2012-02.
- SLP2011 in Tokyo, Japan (Dec. 19-20 2011)
An Open-Source Toolkit Realizing Attractive Voice Interaction Systems: MMDAgent,
Akinobu Lee, Keiichiro Oura, and Keiichi Tokuda,
Technical Report of IEICE, vol.2011-SLP-89, no.27, pp.1-6, 2011-12.
- AXIES 2011 in Hukuoka, Japan (Dec. 07-09 2011)
Campus event entry system for voice interaction digital signage,
Daisuke Yamamoto, Keiichiro Oura, Akinobu Lee, Takahiro Uchiya, Ichi Takumi, Keiichi Tokuda, Hiroshi Matsumoto,
2011-12.
- ASJ2011 autumn in Shimane, Japan (Sep. 20-22 2011)
HMM-based singing voice synthesis using pitch adaptive training,
Ayami Mase, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda,
ASJ2011, vol.I, 1-8-20, pp.283-284, 2010-09.
- Blizzard Challenge 2011 in Turin, Italy (Sep. 02 2011)
Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2011,
Kei Hashimoto, Shinji Takaki, Keiichiro Oura, and Keiichi Tokuda,
Blizzard Challenge 2011, 2011-09.
- ICSLP 2011 in Florence, Italy (Aug. 28-31 2011)
Large-scale Subjective Evaluations of Speech Rate Control Methods for HMM-based Speech Synthesizers,
Makoto Yamada, Nobuyuki Nishizawa, Tsuneo Kato, Keiichiro Oura, Keiichi Tokuda,
ICSLP 2011, pp. 1845-1848, 2011-08.
- ITmedia (Aug. 05 2011)
MMDAgent improved for multi-platform,
ITmedia, 2011-08.
- NITECH PRESS (Jun. 13 2011)
Voice interaction guidance digital signage,
NITECH PRESS, vol. 32, 2011-06.
- Chubu Zaikai (Jun. 01 2011)
Lifelike Digital Signage,
Chubu Zaikai, vol. 54, no. 6, pp.22-23, 2011-06.
- ICASSP 2011 in Prague, Czech (May 22-27 2011)
An optimization algorithm of independent mean and variance parameter tying structures for HMM-based speech synthesis,
Shinji Takaki, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda,
ICASSP 2011, pp. 4700-4703, 2011-03.
- TOKAI Walker (May 10 2011)
MMDAgent - Voice interaction system with 3D character on digital signage,
TOKAI Walker, vol. H23-05-24, 2011-05.
- NITECH RADIO (Feb. 24 2011)
Introduction of the toolkit for building voice interaction system, MMDAgent: Professor Keiichi Tokuda, Associate Professor Akinobu Lee, Assistant Professor Keiichiro Oura,
NITECH RADIO, 2011-02.
- NITECH RADIO (Feb. 23 2011)
Introduction of singing voice synthesis system: Assistant Professor Keiichiro Oura,
NITECH RADIO, 2011-02.
- SCIENCE ZERO (Feb. 05 2011)
Secret of vocal software.
NHK Educational TV, 2011-02.
- NITECH PRESS (Jan. 25 2011)
Speech synthesis engine develped by Tokuda & Lee laboratory was embedded in mobile phone of NTT DoCoMo,
NITECH PRESS, vol. 30, 2011-01.
- ITmedia (Dec. 25 2010)
The alpha release of MMDAgent,
ITmedia, 2010-12.
- NITECH PRESS (Dec. 06 2010)
``MMDAgent'' was shown in CEATEC JAPAN 2010,
NITECH PRESS, vol. 29, 2010-12.
- ICSP2010 in Beijing, China (Oct. 25-28 2010)
Cross-lingual speaker adaptation for HMM-based speech synthesis considering differences between language-dependent average voices,
Xianglin Peng, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda,
ICSP2010, pp.605-608, 2010-10.
- ITmedia (Oct. 07 2010)
The details of MMDAgent,
ITmedia, 2010-10.
- ICSLP2010 in Makuhari, Japan (Sep. 26-30 2010)
HMM-based singing voice synthesis system using pitch-shifted pseudo training data,
Ayami Mase, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda,
ICSLP2010, pp.845-848, 2010-09.
- Blizzard Challenge 2010 in Kyoto, Japan (Sep. 25 2010)
Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2010,
Keiichiro Oura, Kei Hashimoto, Sayaka Shiota, and Keiichi Tokuda,
Blizzard Challenge 2010, 2010-09.
- Open Source Initiatives for Speech Synthesis in Kyoto, Japan (Sep. 24 2010)
Recent development of the HMM-based speech synthesis system (HTS),
Keiichiro Oura, Kei Hashimoto, Heiga Zen, Takashi Nose, Junichi Yamagishi, Shinji Sako, Tomoki Toda, Alan W. Black, and Keiichi Tokuda,
Open Source Initiatives for Speech Synthesis, 2010-09.
- SSW7 in Kyoto, Japan (Sep. 22-24 2010)
Speaker adaptation and the evaluation of speaker similarity in the EMIME speech-to-speech translation project,
Mirjam Wester, John Dines, Matthew Gibson, Hui Liang, Yi-Jian Wu, Lakshmi Saheer, Simon King, Keiichiro Oura, Philip N. Garner, William Byrne, Yong Guan, Teemu Hirsimaki, Reima Karhila, Mikko Kurimo, Matt Shannon, Sayaka Shiota, Jilei Tian, Keiichi Tokuda, and Junichi Yamagishi,
SSW7, pp.192-197, 2010-09.
- SSW7 in Kyoto, Japan (Sep. 22-24 2010)
Recent Development of the HMM-based Singing Voice Synthesis System - Sinsy,
Keiichiro Oura, Ayami Mase, Tomohiko Yamada, Satoru Muto, Yoshihiko Nankaku, and Keiichi Tokuda,
SSW7, pp.211-216, 2010-09.
- ITmedia (Sep. 22 2010)
The future provided by MMDAgent,
ITmedia, 2011-09.
- ASJ2010 autumn in Osaka, Japan (Sep. 14-16 2010)
Subjective evaluations for speech synthesizers trained only from slow speech sounds,
Makoto Yamada, Nobuyuki Nishizawa, Tsuneo Kato, Keiichiro Oura, and Keiichi Tokuda,
ASJ2010 autumn, vol.I, 2-Q-8, pp.315-316, 2010-09.
- ASJ2010 autumn in Osaka, Japan (Sep. 14-16 2010)
An optimization algorithm of mean and variance parameter tying structures for HMM-based speech synthesis,
Shinji Takaki, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda,
ASJ2010 autumn, vol.I, 2-1-8, pp.241-242, 2010-09.
- SIGMUS2010 in Tsukuba, Japan (Jul. 28 2010)
Sinsy - An HMM-based singing voice synthesis system which can realize your wish ``I want this person to sing my song,''
Keiichiro Oura, Ayami Mase, Tomohiko Yamada, Keiichi Tokuda, Masataka Goto,
Technical Report of IPSJ, vol.2010-MUS-86, no.1, pp.1-8, 2010-07.
- ACL 2010 in Uppsala, Sweden (July 13 2010)
Personalising speech-to-speech translation in the EMIME project,
Mikko Kurimo, William Byrne, John Dines, Philip N. Garner, Matthew Gibson, Yong Guan, Teemu Hirsimäki, Reima Karhila, Simon King, Hui Liang, Keiichiro Oura, Lakshmi Saheer, Matt Shannon, Sayaka Shiota, Jilei Tian, Keiichi Tokuda, Mirjam Wester, Yi-Jian Wu and Junichi Yamagishi,
ACL 2010, pp.48-53, 2010-07.
- NITECH PRESS (Jul. 06 2010)
Tokuda & Lee Laboratory was showed in DTM Magazine,
NITECH PRESS, vol. 27, 2010-07.
- IEEE (Jun. 14 2010)
Thousands of Voices for HMM-based Speech Synthesis – Analysis and Application of TTS Systems Built on Various ASR Corpora,
Junichi Yamagishi, Bela Usabaev, Simon King, Oliver Watts, John Dines, Jilei Tian, Yong Guan, Rile Hu, Keiichiro Oura, Yi-Jian Wu, Keiichi Tokuda, Reima Karhila, Mikko Kurimo,
IEEE Transactions on Audio, Speech, and Language Processing, vol.18, no.5, pp.984-1004, 2010-06.
- DTM MAGAZINE (Apr. 08 2010)
A new singing voice synthesis system can learn and reproduce voice quality and singing style automatically: Sinsy,
Keiichi Tokuda, Keiichiro Oura,
DTM MAGAZINE, vol.2010-05, pp.96-97, 2010-04.
- ICASSP2010 in Dallas, USA (May 14-19 2010)
Unsupervised Cross-lingual Speaker Adaptation for HMM-based Speech Synthesis,
Keiichiro Oura, Keiichi Tokuda, Junichi Yamagishi, Mirjam Wester, and Simon King,
ICASSP2010, vol.I, pp.4954-4957, 2010-03.
- ASJ2010 spring in Tokyo, Japan (May 08-10 2010)
Cross-lingual speaker adaptation considering differences between language-dependent average voices,
Xianglin Peng, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda,
ASJ2010 spring, vol.I, 1-7-21, pp.325-326, 2010-03.
- ASJ2010 spring in Tokyo, Japan (May 08-10 2010)
Subjective evaluations of speech rate control methods for HMM-based speech synthesis,
Makoto Yamada, Nobuyuki Nishizawa, Tuneo Kato, Keiichiro Oura, and Keiichi Tokuda,
ASJ2010 spring, vol.I, 1-P-2, pp.405-406, 2010-03.
- ASJ2010 spring in Tokyo, Japan (May 08-10 2010)
Japanese Text-to-Speech Synthesis System: Open JTalk,
Keiichiro Oura, Shinji Sako, and Keiichi Tokuda,
ASJ2010 spring, vol.I, 2-7-6, pp.343-344, 2010-03.
- ASJ2010 spring in Tokyo, Japan (May 08-10 2010)
HMM-based singing voice synthesis system trained by using pitch-shifted pseudo data,
Ayami Mase, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda,
ASJ2010 spring, vol.I, 2-7-7, pp.345-346, 2010-03.
- ASJ2010 spring in Tokyo, Japan (May 08-10 2010)
Reducing computational cost of training for HMM-based singing voice synthesis using note boundaries,
Satoru Muto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda,
ASJ2010 spring, vol.I, 2-7-8, pp.347-348, 2010-03.
- IEICE (May 01 2010)
A Covariance-Tying Technique for HMM-based Speech Synthesis,
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda,
IEICE, vol.E93-D, no.3, pp.595-601, 2010-03.
- Doctor's thesis (Feb. 23 2010)
ACOUSTIC MODELING FOR HMM-BASED SPEECH RECOGNITION AND SYNTHESIS,
Keiichiro Oura, Keiichi Tokuda,
Doctor's thesis (Nagoya Institute of Technology), 2010-02.
- Human Interface (Feb. 01 2010)
Construction of speech synthesis systems using HTS,
Keiichiro Oura, Heiga Zen, Shinji Sako, and Keiichi Tokuda,
Human Interface, vol.12, No.1, pp.35-40, 2010-02.
- SLP2009 in Tokyo, Japan (Dec. 21-22 2009)
Unsupervised Speaker Adaptation for Speech-to-Speech Translation System,
Keiichiro Oura, Junichi Yamagishi, Mirjam Wester, Simon King, and Keiichi Tokuda,
Technical Report of IEICE, vol.2009-SLP-79, no.3, pp.1-6, 2009-12.
- GOKISO (Nov. 11 2009)
Round-table discussion 'Nitech future based on inauguration of business',
Koichiro Kawashima, Tatsuya Tomioka, Osamu Terakura, Tomohiro Hirano, Yohei Yamaguchi, Taizo Umezaki, Keiichiro Oura, and Yukio Niiri,
GOKISO, no.432 pp.12-23, 2009-11.
- APSIPA2009 in Sapporo, Japan (Oct. 04-07 2009)
Recent development of the HMM-based speech synthesis system (HTS),
Heiga Zen, Keiichiro Oura, Takashi Nose, Junichi Yamagishi, Shinji Sako, Tomoki Toda, Takashi Masuko, Alan W. Black, and Keiichi Tokuda,
APSIPA2009, pp.121-130, 2009-10.
- ASJ2009 autumn in Koriyama, Japan (Sep. 15-17 2009)
Unsupervised English-to-Japanese speaker adaptation for HMM-based speech synthesis,
Keiichiro Oura, Junichi Yamagishi, Simon King, Mirjam Wester, and Keiichi Tokuda,
ASJ2009 autumn, vol.I, 3-P-18, pp.401-402, 2009-09.
- The first HTS meeting in Brighton, UK (Sep. 06 2009)
Recent development of the HMM-based speech synthesis system (HTS),
HeigaZen, Keiichiro Oura, Takashi Nose, Junichi Yamagishi, Shinji Sako, Tomoki Toda, Takashi Masuko, Alan W. Black, Keiichi Tokuda,
The first HTS meeting, 2009-09.
- ICSLP2009 in Brighton, UK (Sep. 06-10 2009)
Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems,
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda,
ICSLP2009, pp.1759-1761, 2009-09.
- ICSLP2009 in Brighton, UK (Sep. 06-10 2009)
Thousands of Voices for HMM-based Speech Synthesis,
Junichi Yamagishi, Bela Usabaev, Simon King, Oliver Watts, John Dines, Jilei Tian, Rile Hu, Keiichiro Oura, Keiichi Tokuda, Reima Karhila, and Mikko Kurimo,
ICSLP2009, pp.420-423, 2009-09.
- Blizzard Challenge 2009 in Edinburgh, UK (Sep. 04 2009)
Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2009,
Keiichiro Oura, Yi-Jian Wu, and Keiichi Tokuda,
Blizzard Challenge 2009, 2009-09.
- ISCSLP2008 in Kunming, China (Dec. 16-19 2008)
Simultaneous Acoustic, Prosodic, and Phrasing Model Training for TTS
Conversion Systems,
Keiichiro Oura, Yoshihiko Nankaku, Tomoki Toda, Keiichi Tokuda,
Rannierry Maia, Shinsuke Sakai, and Satoshi Nakamura,
ISCSLP2008, SPE1.1, pp.1-4, 2008-12.
- SLP2008 in Tokyo, Japan (Dec. 09-10 2008)
Tying covariance for HMM-based speech synthesis,
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda,
Technical Report of IEICE, vol.2008-SLP-74, no.123, pp.215-220, 2008-12.
- IEICE (Nov. 01 2008)
A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System,
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda,
IEICE, vol.E91-D, no.11, pp.2693-2700, 2008-11.
- ASJ2008 autumn in Hakata, Japan (Sep. 10-12 2008)
Tying variance for HMM-based speech synthesis,
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda,
ASJ2008 autumn, vol.I, 2-P-29, pp.421-422, 2008-09.
- ASJ2008 spring in Chiba, Japan (Mar. 17-19 2008)
Simultaneous prosody and acoustic model training for english speech synthesis,
Keiichiro Oura, Yoshihiro Nankaku, Tomoki Toda, Keiichi Tokuda, Ranniery Maia, Shinsuke Sakai, and Satoshi Nakamura,
ASJ2008 spring, vol.I, 2-11-1, pp.335-336, 2008-03.
- SLP2007 in Kyoto, Japan (Dec. 20-21 2007)
Recent developments of the HMM-based speech synthesis system (HTS),
Heiga Zen, Keiichiro Oura, Takashi Nose, Junichi Yamagishi, Shinji Sako, Tomoki Toda, Takashi Masuko, Alan W. Black, and Keiichi Tokuda,
Technical Report of IEICE, vol.2007-SLP-69, no.129, pp.301-306, 2007-12.
- ASJ2007 autumn in Kofu, Japan (Sep. 19-21 2007)
Postfiltering for HMM-based speech synthesis using Mel-LSPs,
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda,
ASJ2007 autumn, vol.I, 3-4-9, pp.367-368, 2007-09.
- Master's thesis (Feb. 08 2007)
HSMM Based Speech Recognition Using WFST,
Keiichiro Oura, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda,
Master's thesis (Nagoya Institute of Technology), 2007-02.
- ICASSP2006 in Toulouse, France (May 14-19 2006)
Hidden Semi-Markov Model Based Speech Recognition System Using Weighted Finite-State Transducer,
Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda,
ICASSP2006, vol.I, pp.33-36, 2006-05.
- ASJ2005 autumn in Sendai, Japan (Sep. 27-29 2005)
HSMM Based Speech Recognition Using WFST,
Keiichiro Oura, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda,
ASJ2005 autumn, vol.I, 2-7-15, pp.87-88, 2005-09.
- Graduation thesis (Feb. 15 2005)
CVD-HSMM Based Speech Recognition System Using WFST,
Keiichiro Oura, Keiichi Tokuda, and Tadashi Kitamura,
Graduation thesis (Nagoya Institute of Technology), 2007-02.
|
