Technical reports †

2008 †

• Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Bayesian context clustering using cross validation, Technical Report of IEICE, vol.108, no.338, pp.73--78, Dec. 2008. link

• Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Tying covariance parameters for HMM-based speech synthesis, Technical Report of IEICE, vol.108, no.338, SP2008-115, pp.215-220, Dec. 2008. link

2007 †

• Heiga Zen, Implementing an HSMM-based speech synthesis system using an efficient forward-backward algorithm, Technical Report of Nagoya Institute of Technology, TR-SP-0001, Dec. 2007. paper

• Heiga Zen, Keiichiro Oura, Takashi Nose, Junichi Yamagishi, Shinji Sako, Tomoki Toda, Takashi Masuko, Alan W. Black, Keiichi Tokuda, Recent developments of the HMM-based speech synthesis system (HTS), Technical Report of IEICE, SP2007-147, pp.301-306, Dec. 2007. paper slide (23 MBytes)

• Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Acoutstic modeling based on model structure annealing for speech recognition, Technical Report of IEICE, vol.107, no.165, SP2007-35, pp.67-72, July 2007 (in Japanese).

2006 †

• Heiga Zen, Tomoki Toda, Masaru Nakamura, Keiichi Tokuda, Details of Nitech HMM-based speech synthesis system for Blizzard Challenge 2005, Technical Report of IEICE, SP2006-149, pp.61-66, Jan. 2006. paper

• Heiga Zen, Yoshihiko Nankaku, Tomoki Toda, ICSLP 2006 Summary - Acoustic Modeling and Speech Synthesis -, Technical Report of IEICE, SP2006-115, pp.1-6, Dec. 2006 (in Japanese). paper slide

2003 †

• Heiga Zen, Jinlin Lu, Jinfu Ni, Keiichi Tokuda, Hisashi Kawai, HMM-based prosody modeling and synthesis for Japanese and Chinese speech synthesis, Technical Report of ATR-SLT, TR-SLT-0032, March 2003 (in Japanese).

• Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Decision tree based simultaneous clustering of phonetic contexts, dimensions, and state positions for acoustic modeling, Technical Report of IEICE, SP2003-6, Apr. 2003 (in Japanese). paper

• Yoshihiko Nankaku, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Takashi Masuko, A Bayesian approach to HMM-based speech synthesis, Technical Report of IEICE, SP2003-77, Aug. 2003 (in Japanese).

• Ryosuke Tsuzuki, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Murtaza Bulut, Shrikanth S. Narayanan, Emotional speech modeling in HMM-based speech synthesis, Technical Report of IEICE''', SP2003-78, Aug. 2003 (in Japanese).

• Yohei Itaya, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura, Deterministic annealing EM algorithm for speaker and speech recognition, Technical Report of IEICE''', SP2003-113, Dec. 2003 (in Japanese)

• Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, A trajectory model derived from HMM with explicit relationship between static and dynamic features, Technical Report of IEICE, SP2003-122, Dec. 2003 (in Japanese). paper slide

• Hiroyuki Suzuki, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura, Acoustic modeling in consideration of unknown variation factors at the time of recognition, Technical Report of IEICE, SP2003-139, Dec. 2003.

2001 †

• Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura, A pitch pattern modeling technique using dynamic features on the border of voiced and unvoiced segments, Technical Report of IEICE, SP-69, Sept. 2001 (in Japanese). paper slide