International conference and workshop

2016

  • Keiichi Tokuda, Heiga Zen, Directly modeling voiced and unvoiced components in speech waveforms by neural networks, Proc. ICASSP, pp. 5640--5644, Shanghai, P.R. China, April 2016 filepaper
  • Heiga Zen, Yannis Agiomyrgiannakis, Niels Egberts, Fergus Henderson, Przemysław Szczepaniak, Fast, compact, and high quality LSTM-RNN based statistical parametric speech synthesizers for mobile devices, Proc. Interspeech (accepted), San Francisco, CA, U.S.A., September 2016 filepaper
  • Bo Li, Heiga Zen, Multi-language multi-speaker acoustic modeling for LSTM-RNN based statistical parametric speech synthesis, Proc. Interspeech (accepted), San Francisco, CA, U.S.A., September 2016 filepaper
  • Hideki Kawahara, Yannis Agiomyrgiannakis, Heiga Zen, Using instantaneous frequency and aperiodicity detection to estimate F0 for high-quality speech synthesis, Proc. ISCA SSW9 (submitted), Sunnyvale, CA, U.S.A., September 2016 filepaper

2015

  • Heiga Zen, Hasim Sak, Unidirectional long short-term memory recurrent neural network with recurrent output layer for low-latency speech synthesis, Proc. ICASSP, pp.4470--4474, Brisbane, Australia, April 2015 filepaper
  • Keiichi Tokuda, Heiga Zen, Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis, Proc. ICASSP, pp.4215--4219, Brisbane, Australia, April 2015 filepaper
  • Heiga Zen, Acoustic modeling in statistical parametric speech synthesis - From HMM to LSTM-RNN, Proc. MLSLP, Aizu-Wakamatsu, Japan, September 2015. filepaper

2014

  • Heiga Zen, Andrew Senior, Deep mixture density networks for acoustic modeling in statistical parametric speech synthesis, Proc. ICASSP, pp.3872--3876, Florence, Italy, May 2014. filepaper

2013

  • Heiga Zen, Andrew Senior, Mike Schuster, Statistical parametric speech synthesis using deep neural networks, Proc. of ICASSP, pp.7962--7966, Vancouver, Canada, May 2013. filepaper

2012

  • Cassia Valentini-Botinhao, Ranniery Maia, Junichi Yamagishi, Simon King, Heiga Zen, Cepstral analysis based on the Glimpse proportion measure for improving the intelligibility of HMM-based synthetic speech in noise, Proc of ICASSP, pp.3997--4000, Kyoto, Japan, March 2012.
  • Vincent Wan, Javier Latorre, K. K. Chin, Langzhou Chen, Mark J. F. Gales, Heiga Zen, Kate Knill, Masami Akamine, Combining multiple high quality corpora for improving HMM-TTS, Proc. of Interspeech, pp.1135--1138, Portland, OR, U.S.A., September 2012.

2011

  • Heiga Zen, Mark J. F. Gales, Decision tree-based context clustering based on cross validation and hierarchical priors, Proc. of ICASSP, pp.4560-4563, Prague, Czech, May 2011. filepaper fileslide
  • Matt Shannon, Heiga Zen, William Byrne, The effect of using normalized models in statistical speech synthesis, Proc. of Interspeech, pp.121--124, Florence, Italy, August 2011. filelink
  • Ranniery Maia, Heiga Zen, Kate Knill, Mark J. F. Gales, Sabine Buchholz, Multipulse sequences for residual signal modeling, Proc. of Interspeech, pp.1833--1836, Florence, Italy, August 2011.
  • Ling-Hui Chen, Yoshihiko Nankaku, Heiga Zen, Keiichi Tokuda, Zhen-Hua Ling, Li-Rong Dai, Estimation of window coefficients for dynamic feature extraction for HMM based speech synthesis, Proc. of Interspeech, pp.1801--1804, Florence, Italy, August 2011.
  • Nicholas Pilkington, Heiga Zen, Mark J. F. Gales, Gaussian process experts for voice conversion, Proc. of Interspeech, pp.2761--2764, Florence, Italy, August 2011. filepaper fileposter

2010

  • Heiga Zen, Mark J. F. Gales, Yoshihiko Nankaku, Keiichi Tokuda, Statistical parametric speech synthesis based on product of experts, Proc. of ICASSP2010, pp.4242-4245, Dallas, TX, U.S.A., March 2010. filepaper fileslide
  • Ranniery Maia, Heiga Zen, Mark J. F. Gales, Statistical parametric speech synthesis with joint estimation of acoustic and excitation model parameters, Proc. of ISCA SSW7, pp.88-93, Kyoto, Japan, Sept. 2010.
  • Heiga Zen, Norbert Braunschweiler, Sabine Buchholz, Kate Knill, Sacha Krstulovic, Javier Latorre, HMM-based polyglot speech synthesis by speaker and language adaptive training, Proc. of ISCA SSW7, pp186-191, Kyoto, Japan, Sept. 2010. filepaper fileslide
  • Heiga Zen, Speaker and language adaptive training for HMM-based polyglot speech synthesis, Proc. of Interspeech2010, pp.410-413, Makuhari, Japan, Sept. 2010. filepaper fileslide
  • Kai Yu, Heiga Zen, Francois Mairesse, Steve Young, Context adaptive training with factorized decision trees for HMM-based speech synthesis, Proc. of Interspeech2010, pp.414-417, Makuhari, Japan, Sept. 2010. filelink
  • Nicholas Pilkington, Heiga Zen, An implementation of decision tree-based context clutering on graphics processing units, Proc. of Interspeech2010, pp.833-836, Makuhari, Japan, Sept. 2010. filepaper fileposter
  • Javier Latorre, Mark J.F. Gales, Heiga Zen, Training a parametric-based log F0 model with the minimum generation error criterion, Proc. of Interspeech2010, pp.2174-2177, Makuhari, Japan, Sept. 2010.

2009

  • Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Stereo-based stochastic noise compensation based on trajectory GMMs, Proc. of ICASSP2009, pp.4577-4580, Taipei, Taiwan, April 2009. filepaper fileposter
  • Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Takashi Masuko, Keiichi Tokuda, A Bayesian approach to HMM-based speech synthesis, Proc. of ICASSP2009, pp.4029-4033, Taipei, Taiwan, April 2009. filelink
  • Heiga Zen, Norbert Braunschweiler, Context-dependent additive log F0 model for HMM-based speech synthesis, Proc. of Interspeech2009, pp.2091-2094, Brighton, UK, Sept. 2009. filepaper fileposter
  • Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Tying covariance matrices to reduce the footprint of HMM-based speech synthesis systems, Proc. of Interspeech2009, pp.1759-1762, Brighton, UK, Sept. 2009. filelink
  • Heiga Zen, Keiichiro Oura, Takashi Nose, Junichi Yamagishi, Shinji Sako, Tomoki Toda, Takashi Masuko, Alan W. Black, Keiichi Tokuda, Recent development of the HMM-based speech synthesis system (HTS), Proc. APSIPA ASC 2009, Sapporo, Japan, Oct. 2009 (accepted).

2008

  • Yi-Jian Wu, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Minimum generation error criterion considering global/local variance for HMM-based speech synthesis, Proc. of ICASSP2008, pp.4621-4624, Las Vegas, NV, Mar. 2008.
  • Junichi Yamagishi, Takashi Nose, Heiga Zen, Tomoki Toda, Keiichi Tokuda, Performance evaluation of the speaker-independent HMM-based speech synthesis system "HTS-2007" for the Blizzard Challenge 2007, Proc. of ICASSP2008, pp.3957-3960, Las Vegas, NV, Mar. 2008. filelink
  • Yoshihiko Nankaku, Kazuhiro Nakamura, Heiga Zen, Keiichi Tokuda, Acoustic modeling with contextual additive structure for HMM-based speech recognition, Proc. of ICASSP2008, pp.4469-4472, Las Vegas, NV, Mar. 2008.
  • Junichi Yamagishi, Heiga Zen, Yi-Jian Wu, Tomoki Toda, Keiichi Tokuda, HTS-2008: Yet another evaluation of speaker adaptive HMM-based speech synthesis system, Proc. of Blizzard Challenge Workshop 2008, Brisbane, Australia, Sept. 2008. 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 Interspeech2008, pp.932-035, Brisbane, Australia, Sept. 2008.
  • Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Bayesian context clustering using cross valid prior distribution for HMM-Based speech recognition, Proc. of Interspeech2008, pp,936-939, Brisbane, Australia, Sept. 2008. filelink
  • Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Probabilistic feature mapping based on trajectory HMMs, Proc. of Interspeech2008, pp.1068-1071, Brisbane, Australia, Sept. 2008. filepaper fileposter
  • Simon King, Keiichi Tokuda, Heiga Zen, Junichi Yamagishi, Unsupervised adaptation for HMM-based speech synthesis, Proc. of Interspeech2008, pp.1869-1872, Brisbane, Australia, Sept. 2008.
  • Zhi-Peng Yu, Yi-Jian Wu, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Analysis of stream-dependent tying structure for HMM-based speech synthesis, Proc. of ICSP2008, Beijing, P.R. China, Oct. 2008.

2007

  • Alan W. Black, Heiga Zen, Keiichi Tokuda, Statistical parametric speech synthesis, Proc. of ICASSP2007, pp.1229-1232, Honolulu, Hawaii, Apr. 2007. filepaper fileslide
  • Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Model-space MLLR for trajectory HMMs, Proc. of Interspeech2007, pp.2065-2068, Antwerp, Belgium, Aug. 2007. filepaper fileposter
  • Ranniery Maia, Tomoki Toda, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, A trainable excitation model for HMM-based speech synthesis, Proc. of Interspeech2007, pp.1909-1912, Antwerp, Belgium, Aug. 2007. filelink
  • Heiga Zen, Takashi Nose, Junichi Yamagishi, Shinji Sako, Takashi Masuko, Alan W. Black, Keiichi Tokuda, The HMM-based speech synthesis system version 2.0, Proc. of ISCA SSW6, pp.294-299, Bonn, Germany, Aug. 2007. filepaper fileslide (21 MBytes)
  • Ranniery Maia, Tomoki Toda, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, An excitation model for HMM-based speech synthesis based on residual modeling, Proc. of ISCA SSW6, pp.131-136, Bonn, Germany, Aug. 2007. filelink
  • Junichi Yamagishi, Takao Kobayashi, Steve Renals, Simon King, Heiga Zen, Tomoki Toda, Keiichi Tokuda, Improved average-voice-based speech synthesis using gender-mixed modeling and a parameter generation algorithm considering GV, Proc. of ISCA SSW6, pp.125-130, Bonn, Germany, Aug. 2007. filelink
  • Junichi Yamagishi, Heiga Zen, Tomoki Toda, Keiichi Tokuda, Speaker-Independent HMM-based Speech Synthesis System - HTS-2007 System for the Blizzard Challenge 2007, Proc. of BLZ3-2007, paper 008, Bonn, Germany, Aug. 2007. filelink

2006

  • Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Estimating trajectory HMM parameters using Monte Carlo EM with Gibbs sampler, Proc. of ICASSP2006, pp.1173-1176, Toulouse, France, May 2006. filepaper fileposter
  • Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Hidden semi-Markov model based speech recognition system using weighted finite-state transducer, Proc of ICASSP2006, pp.33-34, Toulouse, France, May 2006. filelink
  • Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Speaker adaptation of trajectory HMMs using feature-space MLLR, Proc. of Interspeech2006 (ICLSP), pp.2274-2277, Pittsburgh, PA, U.S.A., Sept. 2006. filepaper fileposter
  • Keijiro Saino, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, HMM-based singing voice synthesis system, Proc. of Interspeech2006 (ICSLP), pp.1141-1144, Pittsburgh, PA, U.S.A., Sept. 2006. filelink
  • Heiga Zen, Tomoki Toda, Keiichi Tokuda, The Nitech-NAIST HMM-based speech synthesis system for the Blizzard Challenge 2006, Proc. of BLZ2-2006, Pittsburgh, PA, U.S.A., Sept. 2006. filepaper fileslide filelink
  • Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda, Hyperparameter estimation for speech recognition based on variational Bayesian approach, Proc. ASA & ASJ Joint Meeting, pp.3042, Honolulu, Hawaii, Dec. 2006. filelink

2005

  • Amaro Lima, Heiga Zen, Yoshihiko Nankaku, Keiichi Tokuda, Tadashi Kitamura, Sparse KPCA for feature extraction in speech recognition, Proc. of ICASSP2005, vol.I, pp.353-356, Philadelphia, PA, U.S.A., Mar. 2005. filelink
  • Heiga Zen, Tomoki Toda, An overview of Nitech HMM-based speech synthesis system for Blizzard Challenge 2005, Proc. of Interspeech2005 (Eurospeech), pp.93-96, Lisbon, Sept. 2005. filepaper fileslide
  • Wael Hamza, Raimo Bakis, Zhang-Wei Shuang, Heiga Zen, On building a concatenative speech synthesis system from the Blizzard Challenge speech databases, Proc. of Interspeech2005 (Eurospeech), pp.97-100, Lisbon, Sept. 2005. filelink

2004

  • Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, A Viterbi algorithm for a trajectory model derived from HMM with explicit relationship between static and dynamic features, Proc. of ICASSP 2004, pp.837-840, Montreal, May 2004. filepaper fileposter
  • Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, An introduction of trajectory model into HMM-based speech synthesis, Proc. of 5th ISCA Speech Synthesis Workshop, Pittsburgh, June 2004. filepaper fileposter
  • Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura, Hidden semi-Markov model based speech synthesis, Proc. of ICSLP 2004, vol.II, pp.1397-1400, Jeju, Oct. 2004. filepaper fileslide
  • Yohei Itaya, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura, Deterministic annealing EM algorithm in parameter estimation for acoustic model, Proc. of ICSLP 2004, vol.I, pp.433-436, Jeju, Oct. 2004. filepaper
  • Ryosuke Tsuzuki, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Murtaza Bulut, Shrikanth S. Narayanan, Constructing emotional speech synthesizers with limited speech database, Proc. of ICSLP 2004, vol.II, pp.1185-1188, Jeju, Oct. 2004. filepaper
  • Keiichi Tokuda, Heiga Zen, Tadashi Kitamura, Reformulating the HMM as a trajectory model, Proc. of Beyond HMM -- Workshop on statistical modeling approach for speech recognition, Kyoto, Dec. 2004. filepaper fileposter

2003

  • Hiroyuki Suzuki, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura, Speech recognition using voice-characteristic dependent acoustic model, Proc. of ICASSP 2003, vol.1, pp.740-743, Apr. 2003. filepaper
  • Takahiro Hoshiya, Shinji Sako, Heiga Zen, Keiichi Tokuda, Takashi Masuko, Takao Kobayashi, Tadashi Kitamura, Improving the performance of HMM-based very low bitrate speech coding, Proc. of ICASSP 2003, vol.1, pp.800-803, Apr. 2003. filepaper
  • Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Decision tree based simultaneous clustering of phonetic contexts, dimensions, and state positions for acoustic modeling, Proc. of Eurospeech 2003, pp.3189-3192, Sept. 2003. filepaper fileposter
  • Keiichi Tokuda, Heiga Zen, Tadashi Kitamura, Trajectory modeling based on HMMs with the explicit relationship between static and dynamic features, Proc. of Eurospeech 2003, pp.865-868, Sept. 2003. filepaper
  • Ranniery S. Maia, Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Towards the development of a Brazilian Portuguese text-to-speech system based on HMM, Proc. of Eurospeech 2003, pp.2465-2468, Sept. 2003. filelink
  • Amaro Lima, Heiga Zen, Yoshihiko Nankaku, Chiyomi Miyajima, Keiichi Tokuda, Tadashi Kitamura, On the use of kernel PCA for feature extraction in speech recognition, Proc. of Eurospeech 2003, pp.2625-2628, Sept. 2003. filelink

2002

  • Heiga Zen, Keiichi Tokuda, Tadashi Kitamura, Decision tree distribution tying based on a dimensional split technique, Proc. of ICSLP 2002, pp.1257-1260, Sept. 2002. filepaper fileslide
  • Keiichi Tokuda, Heiga Zen, Alan W. Black, An HMM-based speech synthesis system applied to English, Proc. of IEEE Speech Synthesis Workshop, Sept. 2002. filelink

Attach file: filezen-ssw5.pdf 779 download [Information] filezen-ssw6.pdf 3948 download [Information] filezen-ssw7-slide.pdf 1841 download [Information] filezen-ssw7.pdf 1954 download [Information] filezen-trjMapping-bham09.pdf 2037 download [Information] filezen-interspeech09.pdf 1908 download [Information] filezen-interspeech09-poster.pdf 2045 download [Information] filezen-interspeech2010-slide.pdf 1302 download [Information] filezen-icslp08.pdf 2070 download [Information] filezen-interspeech2010.pdf 1279 download [Information] filezen-ssw5-poster.pdf 2975 download [Information] filezen-icslp02.pdf 1858 download [Information] filezen-icassp2011.pdf 1211 download [Information] filezen-icslp04.pdf 2657 download [Information] filezen-icslp02-slide.pdf 1864 download [Information] filezen-icslp04-slide.pdf 2756 download [Information] filezen-icslp08-poster.pdf 2967 download [Information] filezen-icslp06-poster.pdf 2471 download [Information] filezen-icslp06.pdf 2442 download [Information] filezen-icassp2010-slide.pdf 1394 download [Information] filezen-icassp2010.pdf 1279 download [Information] filezen-icassp2011-slide.pdf 1322 download [Information] filezen-icassp09.pdf 1462 download [Information] filezen-icassp09-poster.pdf 2069 download [Information] filezen-icassp06.pdf 2496 download [Information] filezen-icassp06-poster.pdf 2572 download [Information] filezen-icassp04.pdf 2397 download [Information] filetokuda-euro03.pdf 2091 download [Information] filezen-blizzard06.pdf 2139 download [Information] filetokuda-beyondHMM.pdf 1962 download [Information] filesuzuki-icassp03.pdf 3617 download [Information] filezen-euro03-poster.pdf 2012 download [Information] filetokuda-beyondHMM-poster.pdf 1807 download [Information] filezen-blizzard06-slide.pdf 1667 download [Information] filezen-icassp04-poster.pdf 1893 download [Information] filezen-euro03.pdf 2379 download [Information] filezen-euro07.pdf 2339 download [Information] filezen-euro07-poster.pdf 2109 download [Information] filezen-euro05-slide.pdf 1586 download [Information] filezen-euro05.pdf 2335 download [Information] filehoshiya-icassp03.pdf 3291 download [Information] fileitaya-icslp04.pdf 3469 download [Information] fileawb-icassp07.pdf 4519 download [Information] filepilkington-interspeech2010-poster.pdf 1498 download [Information] fileryosuke-icslp04.pdf 2250 download [Information] fileawb-icassp07-slide.pdf 5431 download [Information] filepilkington-interspeech2011.pdf 1698 download [Information] filepilkington-interspeech2011-poster.pdf 778 download [Information] filepilkington-interspeech2010.pdf 1822 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: 2016-07-12 (Tue) 16:20:12 (494d)