Domestic conferences

2011

  • Masatsune Tamura, Sacha Krstulovic, Ryo Morinaka, Ryutaro Tokuda, Heiga Zen, Masahiro Morita, Takehiko Kagoshima, Masami Akamine, Development of US English text-to-speech synthesizer using HMM-based speech synthesis, Prof. of Spring Meeting of the ASJ, vol.I, pp.313-314, 3-7-7, March 2011 (in Japanese).

2009

  • Kyohei Nagao, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Investigation of global variance modeling for HMM-based speech synthesis, Prof. of Spring Meeting of the ASJ, vol.I, pp.427-428, 1-R-19, March 2009 (in Japanese).

2008

  • Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Context clustering using cross validation based on Bayesian criterion, Proc. of Spring Meeting of the ASJ, vol. I, pp. 69-70, 2-10-2, March 2008 (in Japanese). filelink
  • Junichi Yamagishi, Takashi Nose, Heiga Zen, Tomoki Toda, Keiichi Tokuda, Takao Kobayashi, Performance evaluation of average-voice based speech synthesis system for Blizzard Challenge 2007, Proc. of Spring Meeting of the ASJ, vol. I, pp. 339-342, 2-11-3, March 2008 (in Japanese).
  • Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Tying variance for HMM-based speech synthesis, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 421-422, 2-P-29, Sept. 2008 (in Japanese). filelink
  • Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, HMM based speech synthesis using cross validation for Bayesian criterion, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 251-252, 1-4-7, Sept. 2008 (in Japanese). filelink

2007

  • Heiga Zen, Takashi Nose, Junichi Yamagishi, Shinji Sako, Keiichi Tokuda, The HMM-based speech synthesis system version 2.0, Proc. of Spring Meeting of the ASJ, March 2007. filepaper fileslide
  • Ranniery Maia, Tomoki Toda, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Mixed excitation for HMM-based speech synthesis based on state-dependent filtering, Proc. of Spring Meeting of the ASJ, vol. I, pp. 199-200, 1-8-4, March 2007.
  • Toshiaki Watanabe, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Reducing computational complexity of a synthesis filter for HMM-based speech synthesis, Proc. of Spring Meeting of the ASJ, vol. I, pp. 209-210, 1-8-9, March 2007 (in Japanese).
  • Kazuhiro Nakamura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Decision-tree based state clustering considering context-dependent additive structure, Proc. of Spring Meeting of the ASJ, vol. I, pp. 149-150, 1-P-13, March 2007 (in Japanese).
  • Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Speaker adaptation of trajectory HMMs using model-space MLLR, Proc. of Autumn Meeting of the ASJ, 2-3-15, September 2007 (in Japanese). filepaper fileslide
  • Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Hyper-parameter tying structure for speech recognition based on variational Bayesian method, Proc. of Autumn Meeting of the ASJ, 3-3-4, September 2007 (in Japanese). filelink
  • Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Acoustic Modeling Based on Model Structure Annealing for Speech Recognition, Proc. of Autumn Meeting of the ASJ, 3-3-5, September 2007 (in Japanese).
  • Keijiro Saino, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, An HMM-based speech synthesis with eigenvoice model using factor analysis, Autumn Meeting of the ASJ, 3-4-8, September 2007 (in Japanese).
  • Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Postfiltering for HMM-based speech synthesis using Mel-LSPs, Proc. of Autumn Meeting of the ASJ, 3-4-9, September 2007 (in Japanese). filelink
  • Yi-Jian Wu, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Evaluation of parameter optimization methods for minimum generation error based HMM training, Proc. of Autumn Meeting of the ASJ, 3-4-10, September 2007.

2006

  • Heiga Zen, Tomoki Toda, Keiichi Tokuda, The Nitech-NAIST HMM-based speech synthesis system for the Blizzard Challenge 2006, Proc. of Autumn Meeting of the ASJ, Sept. 2006. filepaper fileslide
  • Masahiro Marume, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, An investigation of spectral paremeter for HMM-based speech synthesis, Proc. of Autumn Meeting of the ASJ, Sept. 2006 (in Japanese).
  • Yoshihiro Itogawa, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Tadashi Kitamura, An implementation of speaker-dependent 100bit/s speech coder based on HMM for English, Proc. of Spring Meeting of the ASJ, vol. I, pp. 193-194, 1-1-20, March 2006 (in Japanese).

2005

  • Shunsuke Kataoka, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Simultaneous backing-off of spectrum, f0 and duration decision trees in HSMM-based speech synthesis, Proc. of Spring Meeting of the ASJ, vol. I, pp. 193-194, 1-1-20, March 2005 (in Japanese).
  • Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, An EM-type training algorithm for trajectory-HMM using Gibbs sampling, Proc. of Autumn Meeting of the ASJ, 2-7-16, Sept. 2005 (in Japanese). filepaper fileslide
  • Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Speaker adaptation of trajectory-HMM using constrained MLLR, Proc. of Autumn Meeting of the ASJ, 3-7-6, Sept. 2005 (in Japanese). filepaper fileslide
  • Masaru Nakamura, Heiga Zen, Tomoki Toda, Keiichi Tokuda, An evaluation of improvements of HMM-based speech synthesis system for Blizzard Challenge 2005, Proc. of Autumn Meeting of the ASJ, 3-6-18, Sept. 2005 (in Japanese).

2004

  • Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura, HMM parameter reestimation with explicit duration model for HMM-based speech synthesis, Proc. of Spring Meeting of the ASJ, vol. I, pp. 223-224, 1-7-6, March 2004 (In Japanese). filepaper fileslide
  • Ryosuke Tsuzuki, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Murtaza Bulut, Shrikanth S. Narayanan, Emotional speech synthesis based on HMM using subjective evaluation, Proc. of Spring Meeting of the ASJ, vol. I, pp. 251-252, 1-7-20, March 2004 (In Japanese).
  • Amaro Lima, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Fernand G. V. Resende Jr., Feature extraction for speech recognition using sparse KPCA, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 69-70, 2-1-17, Sept. 2004.
  • Hiroaki Kuwabara, Ryosuke Tsuzuki, Heiga Zen, Shinji Sako, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, A study on designing context-dependent labels based on musical score for HMM-based singing voie synthesis, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 323-324, 3-2-4, Sept. 2004 (in Japanese).
  • Yusuke Morioka, Shunsuke Kataoka, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Minutuarization of HMM-based speech synthesis, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 325-326, 3-2-5, Sept. 2004 (in Japanese).

2003

  • Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, A trajectory model derived from continuous density HMM with static and dynamic features, Proc. of Spring Meeting of the ASJ, 1-4-7, March 2003 (In Japanese). filepaper fileslide
  • Yuka Kishimoto, Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura, Automatic estimation of postfilter coefficients for HMM-based speech synthesis, Proc. of Spring Meeting of the ASJ, 1-6-11, March 2003 (In Japanese).
  • Heiga Zen, Keiichi Tokuda, Hisashi Kawai, Designing texts for speech synthesis corpus by sentence generation from language model, Proc. of Spring Meeting of the ASJ, 1-6-18, March 2003 (In Japanese). filepaper fileslide
  • Ryosuke Tsuduki, Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura, A study on HMM-based emotional speech synthesis, Proc. of Spring Meeting of the ASJ, 1-6-24, March 2003 (In Japanese).
  • Tsuyoshi Ishikawa, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura, Bimodal continuous speech recognition using late integration method based on acoustic likelihood rescoring, Proc. of Spring Meeting of the ASJ, 3-Q-21, March 2003 (In Japanese).
  • Hiroyuki Suzuki, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura, Speech recognition using acoustic models depend on noise environments, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 25-26, 1-6-13, Sept. 2003 (In Japanese).
  • Yoshihiko Nankaku, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Takashi Masuko, Speech synthesis based on variational Bayesian HMM, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 207-208, 1-8-13, Sept. 2003 (In Japanese).
  • Ranniery da S. Maia, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Fernand G. V. Resende Jr., On the application of HMM-based speech synthesis to Brazilian Portuguese , Proc. of Autumn Meeting of the ASJ, vol. I, pp. 215-216, 1-8-17, Sept. 2003 (In Japanese).
  • Kikuo Emoto, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Accent type recognition for automatic prosodic labeling , Proc. of Autumn Meeting of the ASJ, vol. I, pp. 225-226, 1-8-22, Sept. 2003 (In Japanese).
  • Ryosuke Tsuzuki, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Murtaza Bulut, Shrikanth S. Narayanan, A study on emotional speech synthesis based on HMM, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 241-242, 2-6-4, Sept. 2003 (In Japanese).
  • Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, A Viterbi algorithm for trajectory HMM, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 65-66, 2-6-3, Sept. 2003 (In Japanese). filepaper fileslide
  • Yohei Itaya, Heiga Zen, Yoshihiko Nankaku, C. Miyajima, Keiichi Tokuda, Tadashi Kitamura, Continuous speech recognition using HMM based on DAEM algorithm , Proc. of Autumn Meeting of the ASJ, vol. I, pp. 67-68, 2-6-4, Sept. 2003 (In Japanese).
  • Masatoshi Sugiura, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Context clustering based on maximum mutual information criterion, Proc. of Autumn Meeting of the ASJ, vol. I, pp. 69-70, 2-6-5, Sept. 2003 (In Japanese).

2002

  • Heiga Zen, Keiichi Tokuda, T. Masuko, T. Kobayashi, Tadashi Kitamura, Speech synthesis from partial shared HMMs, Proc. of Spring Meeting of the ASJ, 1-10-3, March 2002 (In Japanese). filepaper fileslide
  • Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, HMM state partial sharing method based on tree-based clustering, Proc. of Spring Meeting of the ASJ, 2-5-2, March 2002 (In Japanese). filepaper fileslide
  • A. Lima, Heiga Zen, Yoshihiko Nankaku, C. Miyajima, Keiichi Tokuda, Tadashi Kitamura, On the use of KPCA for feature extraction in speech recognition, Proc. of Autumn Meeting of the ASJ, 1-9-4, Sept. 2002.
  • H. Suzuki, Heiga Zen, Yoshihiko Nankaku, C. Miyajima, Keiichi Tokuda, Tadashi Kitamura, Speech recognition using voice characteristic dependent acoustic models, Proc. of Autumn Meeting of the ASJ, 1-9-19, Sept. 2002 (In Japanese).
  • Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Decision tree based simultaneous clustering of phonetic context, dimension, and state position, Proc. of Autumn Meeting of the ASJ, 1-9-20, Sept. 2002 (In Japanese). filepaper
  • T. Hoshiya, S. Sako, Heiga Zen, Keiichi Tokuda, T. Masuko, T. Kobayashi, Tadashi Kitamura, Improving the performance of HMM-based very low bitrate speech coding, Proc. of Autumn Meeting of the ASJ, 1-10-3, Sept. 2002 (In Japanese).
  • Y. Kishimoto, Heiga Zen, Keiichi Tokuda, T. Masuko, T. Kobayashi, Tadashi Kitamura, A postfiltering technique for HMM-based speech synthesis, Proc. of Autumn Meeting of the ASJ, 2-1-1, Sept. 2002 (In Japanese).
  • Heiga Zen, T. Yoshimura, M. Tamura, T. Masuko, Keiichi Tokuda, A toolkit for HMM-based speech synthesis, Proc. of Autumn Meeting of the ASJ, 3-10-14, Sept. 2002 (In Japanese). filepaper fileslide
  • Keiichi Tokuda, Heiga Zen, A. W. Black, An HMM-based approach to English speech synthesis, Proc. of Autumn Meeting of the ASJ, 3-10-15, Sept. 2002.
  • T. Ishikawa, Y. Sawada, Heiga Zen, Yoshihiko Nankaku, C. Miyajima, Keiichi Tokuda, Tadashi Kitamura, Audio-visual large vocabulary continuous speech recognition based on early integration, Proc. of Meeting of the Forum of Information Technology, Sept., 2002 (In Japanese).

2001

  • Heiga Zen, Keiichi Tokuda, T. Masuko, T. Kobayashi, Tadashi Kitamura, An accurate modeling method of pitch pattern considering dynamic features, Proc. of Autumn Meeting of the ASJ, 1-2-7, Oct. 2001 (In Japanese). filepaper fileslide

Attach file: filezen-asj0709-slide.pdf 3337 download [Information] filezen-asj0709.pdf 2595 download [Information] filezen-asj0509-MCEM-slide.pdf 2907 download [Information] filezen-asj0509-CMLLR.pdf 2286 download [Information] filezen-asj0403.pdf 2711 download [Information] filezen-asj0509-MCEM.pdf 3036 download [Information] filezen-asj0509-CMLLR-slide.pdf 4205 download [Information] filezen-asj0609-slide.pdf 1990 download [Information] filezen-asj0703.pdf 4680 download [Information] filezen-asj0703-slide.pdf 9066 download [Information] filezen-asj0609.pdf 2955 download [Information] filezen-asj0403-slide.pdf 2102 download [Information] filezen-asj0309.pdf 3498 download [Information] filezen-asj0309-slide.pdf 2504 download [Information] filezen-asj0209-PDSDT.pdf 3458 download [Information] filezen-asj0209-HTS-slide.pdf 1983 download [Information] filezen-asj0203-HTS.pdf 2609 download [Information] filezen-asj0303-trjHMM-slide.pdf 2247 download [Information] filezen-asj0209-HTS.pdf 5820 download [Information] filezen-asj0303-trjHMM.pdf 3000 download [Information] filezen-asj0303-txtGen-slide.pdf 2363 download [Information] filezen-asj0303-txtGen.pdf 2457 download [Information] filezen-asj0110.pdf 3141 download [Information] filezen-asj0203-CSR-slide.pdf 2039 download [Information] filezen-asj0203-CSR.pdf 2488 download [Information] filezen-asj0203-HTS-slide.pdf 2114 download [Information] filezen-asj0110-slide.pdf 2533 download [Information]

Front page   Edit Freeze Diff Backup Upload Copy Rename Reload   New List of pages Search Recent changes   Help   RSS of recent changes
Last-modified: 2015-10-06 (Tue) 13:08:25 (1379d)