PUBLICATIONS - 2009
Journal
- Kei Hashimoto, Hirohumi Yamamoto, Hideo Okuma, Eiichiro Sumita, and Keiichi Tokuda, ``A reordering model using a source-side parse-tree for statistical machine translation,'' IEICE Transactions on Information and Systems, vol. E92-D, no. 12, pp. 2386-2393, December, 2009. (Full paper peer reviewed)
- Heiga Zen, Keiichi Tokuda, and Alan W. Black, ``Statistical parametric speech synthesis,'' Speech Communication, vol. 51, no. 11, pp. 1039-1154, November, 2009. (Full paper peer reviewed)
link
- Junichi Yamagishi, Takashi Nose, Heiga Zen, Zhen-Hua Ling, Tomoki Toda, Keiichi Tokuda, Simon King, Steve Renals, ``A robust speaker-adaptive HMM-based text-to-speech synthesis,'' IEEE Transactions on Audio, Speech, and Language Processing, vol. 17, no. 6, August, 2009. (Full paper peer reviewed)
- Heiga Zen, and Keiichi Tokuda, ``TechWare: HMM-Based Speech Synthesis Resources,'' IEEE Signal Processing Magazine, July, 2009. (Review paper)
link
- Kiyohiro Shikano , Kazuya Takeda, Tatsuya Kawahara,Hideki Kawahara, Hiroshi Saruwatari, Keiichi Tokuda, Akinobu Lee, Hiromichi Kawanami, Ryuichi Nisimura, Randy Gomez, Tomoki Toda, Takanobu Nishiura, Toru Takahashi, Hideki Banno, Heiga Zen, ``E-Society Software Development Project for Speech Recognition and Synthesis(Technical Report),'' vol. 92, no. 6, 2009. (Invited paper)
International Conference
- Heiga Zen, Keiichiro Oura, Takashi Nose, Junichi Yamagishi, Shinji Sako, Tomoki Toda, Takashi Masuko, Alan W. Black, and Keiichi Tokuda, ``Recent development of the HMM-based speech synthesis system (HTS),'' Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference (APSIPA ASC 2009), pp. 121-130, Sapporo, Japan, October, 2009. (Invited session paper)
link
- Junichi Yamagishi, Bela Usabaev, Simon King, Oliver Watts, John Dines, Jilei Tian, Rile Hu, Yong Guan, Keiichiro Oura, Keiichi Tokuda, Reima Karhila, and Mikko Kurimo ``Thousands of voices for HMM-based speech synthesis,'' Interspeech 2009, pp. 420-423, Brighton, U.K., September 6-10, 2009. (Full paper peer reviewed)
- Yi-Jian Wu, Yoshihiko Nankaku, and Keiichi Tokuda, ``State mapping based method for crosslingual speaker adaptation in HMM-based speech synthesis,'' Interspeech 2009, pp. 528-531, Brighton, U.K., September 6-10, 2009. (Full paper peer reviewed) link
- Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Deterministic annealing based training algorithm for Bayesian speech recognition,'' Interspeech 2009, pp. 680-683, Brighton, U.K., September 6-10, 2009. (Full paper peer reviewed)
link
- Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A Bayesian approach to hidden Semi-Markov model based speech synthesis,'' Interspeech 2009, pp. 1751-1754, Brighton, U.K., September 6-10, 2009. (Full paper peer reviewed)
link
- Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems,'' Interspeech 2009, pp. 1759-1761, Brighton, U.K., September 6-10, 2009. (Full paper peer reviewed)
- Ranniery Maia, Tomoki Toda, Keiichi Tokuda, Shinsuke Sakai, and Satoshi Nakamura, ``A decision tree-based clustering approach to state definition in an excitation modeling framework for HMM-based speech synthesis,'' Interspeech 2009, pp. 1783-1786, Brighton, U.K., September 6-10, 2009. (Full paper peer reviewed)
- Yi-Jian Wu, Long Qin, and Keiichi Tokuda, ``An improved minimum generation error based model adaptation for HMM-based speech synthesis,'' Interspeech 2009, pp. 1787-1790, Brighton, U.K., September 6-10, 2009. (Full paper peer reviewed)
link
- Keiichiro Oura, Yi-Jian Wu , and Keiichi Tokuda, ``Overview of NIT HMM-based speech synthesis system for Blizzard Challenge 2009,'' 2009 Blizzard Challenge Workshop, September, 2009 (web proceedings).
link
- Kei Hashimoto, Hirohumi Yamamoto, Hideo Okuma, Eiichiro Sumita, and Keiichi Tokuda, ``Reordering model using syntactic information of a source tree for statistical machine translation,'' NAACL HLT 2009 Workshop: Third Workshop on Syntax and Structure in Statistical Translation (SSST-3), pp. 69-77, Boulder, Colorado, June, 2009. (Full paper peer reviewed)
- Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, and Keiichi Tokuda, ``A Bayesian approach to HMM-based speech synthesis,'' 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009), pp. 4029-4032, Taipei, Taiwan, April, 2009. (Full paper peer reviewed)
link
- Yi-Jian Wu, and Keiichi Tokuda, ``Minimum generation error training by using original spectrum as reference for log spectral distortion measure,'' 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009), pp. 4013-4016, Taipei, Taiwan, April, 2009. (Full paper peer reviewed)
link
- Kaori Yutani, Yosuke Uto, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``Voice conversion based on simultaneous modeling of spectrum and F0,'' 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009), pp. 3897-3900, Taipei, Taiwan, April, 2009. (Full paper peer reviewed)
- Heiga Zen, Yoshihiko Nankaku, and Keiichi Tokuda, ``Stereo-based stochastic noise compensation based on trajectory GMMs,'' 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009), pp. 4577-4580, Taipei, Taiwan, April, 2009. (Full paper peer reviewed)
- Lu Heng, Wu Yi-Jian, Tokuda Keiichi, Dai Li-Rong, and Wang Ren-Hua, ``FULL covariance state duration modeling for HMM-based speech synthesis,'' 2009 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009), pp. 4033-4036, Taipei, Taiwan, April, 2009. (Full paper peer reviewed)
link
Past Publications