PUBLICATIONS - 2008
Journal
- Kiyohiro Shikano, Tatsuya Kawahara, Hiroshi Saruwatari, Kazuya Takeda, Hideki Kawahara, Keiichi Tokuda,Takanobu Nishiura, Akinobu Lee,``Development of Advanced Development of Fundamental Software through Tight Collaboration of Academia and Industry:Human Friendly Speech Interface ,'' The Information Processing Society of Japan , vol. 49, no. 11, pp. 1297-1301, 2008年11月. (Tutorial paper) (in Japanese)
- Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``A Fully Consistent Hidden Semi-Markov Model-Based Speech Recognition System,'' IEICE Transactions on Information and Systems, vol. E91-D, no. 11, pp. 2693-2700, November, 2008. (Full paper peer reviewed)
- Heiga Zen, Tomoki Toda, and Keiichi Tokuda, ``The Nitech-NAIST HMM based speech synthesis system for the Blizzard Challenge 2006,'' IEICE Transactions on Information and Systems, vol. E91-D, no. 6, pp. 1764-1773, June, 2008. (Full paper peer reviewed)
- Tomoki Toda, Alan W. Black, and Keiichi Tokuda, ``Statistical mapping between articulatory movements and acoustic spectrum with a Gaussian mixture model,'' Speech Communication, vol. 50, no. 3, pp. 215-227, March, 2008. (Full paper peer reviewed)
International Conference
- Yi-Jian Wu, Simon King and Keiichi Tokuda, ``Cross-lingual speaker adaptation for HMM-based speech synthesis,'' International Symposium on Chinese Spoken Language Processing (ISCSLP2008), SPE1.1, pp. 9-12, Kunming, China, December, 2008. (Full paper peer reviewed)
link
- Keiichiro Oura, Yoshihiko Nankaku, Tomoki Toda, Keiichi Tokuda, Rannierry Maia, Shinsuke Sakai, and Satoshi Nakamura, ``Simultaneous acoustic, prosodic, and phrasing model training for TTS conversion systems,'' International Symposium on Chinese Spoken Language Processing (ISCSLP2008), SPE1.1, pp. 1-4, Kunming, China, December, 2008. (Best Student Paper Award, Full paper peer reviewed)
link
- Zhi-Peng Yu, Yi-Jian Wu, Heiga Zen, Yoshihiko Nankaku, and Keiichi Tokuda, ``Analysis of stream-dependent tying structure for HMM-based speech synthesis,'' International Conference on Signal Processing (ICSP’08), pp. 655-658, Beijing, China, October, 2008. (Full paper peer reviewed)
link
- Junichi Yamagishi, Heiga Zen, Yi-Jian Wu, Tomoki Toda, and Keiichi Tokuda, ``HTS-2008: Yet another evaluation of speaker adaptive HMM-based speech synthesis system,'' Blizzard Challenge Workshop 2008, Brisbane, Australia, September, 2008. (web proceedings)
- Ranniery Maia, Jinfu Ni, Shinsuke Sakai, Tomoki Toda, Keiichi Tokuda, Tohru Shimizu, and Satoshi Nakamura, ``The NICT/ATR speech synthesis system for the Blizzard Challenge 2008,'' Blizzard Challenge Workshop 2008, Brisbane, Australia, September, 2008. (web proceedings)
- Yoshitaka Yoshimi, Ryota Kakitsuba, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``Probabilistic answer selection based on conditional random fields for spoken dialog system,'' Interspeech 2008, pp. 215-218, Brisbane, Australia, September, 2008. (Full paper peer reviewed)
- Yi-Jian Wu, and Keiichi Tokuda, ``Minimum generation error training with direct log spectral distortion on LSPs for HMM-Based speech synthesis,'' Interspeech 2008, pp. 577-580, Brisbane, Australia, September, 2008. (Full paper peer reviewed)
link
- Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``Acoustic modeling based on model structure annealing for speech recognition,'' Interspeech 2008, pp. 932-935, Brisbane, Australia, September, 2008. (Full paper peer reviewed)
- Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``Bayesian context clustering using cross valid prior distribution for HMM-Based speech recognition,'' Interspeech 2008, pp. 936-939, Brisbane, Australia, September, 2008. (Full paper peer reviewed)
- Heiga Zen, Yoshihiko Nankaku, and Keiichi Tokuda, ``Probabilistic feature mapping based on trajectory HMMs,'' Interspeech 2008, pp. 1068-1071, Brisbane, Australia, September, 2008. (Full paper peer reviewed)
- Kaori Yutani, Yosuke Uto, Yoshihiko Nankaku, Tomoki Toda, and Keiichi Tokuda, ``Simultaneous conversion of duration and spectrum based on statistical models including time sequence matching,'' Interspeech 2008, pp. 1072-1075, Brisbane, Australia, September, 2008. (Full paper peer reviewed)
- Tatsuya Ito, Kei Hashimoto, Yoshihiko Nankaku, Akinobu Lee, and Keiichi Tokuda, ``Speaker recognition based on variational bayesian method,'' Interspeech 2008, pp. 1417-1420, Brisbane, Australia, September, 2008. (Full paper peer reviewed)
- Simon King, Keiichi Tokuda, Heiga Zen, and Junichi Yamagishi, ``Unsupervised adaptation for HMM-Based speech synthesis,'' Interspeech 2008, pp. 1869-1872, Brisbane, Australia, September, 2008. (Full paper peer reviewed)
- Yi-Jian Wu, Heiga Zen, Yoshihiko Nankaku, and Keiichi Tokuda, ``Minimum generation error criterion considering global/local variance for HMM-based speech synthesis,'' 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), pp. 4621-4624, Las Vegas, Nevada, U.S.A., March 30- April 4, 2008. (Full paper peer reviewed)
link
- Yoshihiko Nankaku, Kazuhiro Nakamura, Heiga Zen, and Keiichi Tokuda, ``Acoustic modeling with contextual additive structure for HMM-based speech recognition,'' 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), pp. 4469-4472, Las Vegas, Nevada, U.S.A., March 30- April 4, 2008. (Full paper peer reviewed)
- Junichi Yamagishi, Takashi Nose, Heiga Zen, Tomoki Toda, and Keiichi Tokuda, ``Performance evaluation of the speaker-independent HMM-based speech synthesis system HTS-2007 for the Blizzard Challenge 2007,'' 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), pp. 3957-3960, Las Vegas, Nevada, U.S.A., March 30- April 4, 2008. (Full paper peer reviewed)
- Ranniery Maia, Tomoki Toda, Keiichi Tokuda, Shinsuke Sakai, and Satoshi Nakamura, ``On the state definition for a trainable excitation model in HMM-based speech synthesis,'' 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), pp. 3965-3968, Las Vegas, Nevada, U.S.A., March 30- April 4, 2008. (Full paper peer reviewed)
- Tomoki Toda, and Keiichi Tokuda, ``Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM,'' 2008 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2008), pp. 3925-3928, Las Vegas, Nevada, U.S.A., March 30- April 4, 2008. (Full paper peer reviewed)
- Tomoki Toda ,Alan.W.Black Keiichi Tokuda,``Statistical Mapping between Articulatory Movements and Acoustic Spectrum Using a Gaussian Mixture Model,'' Nara Institute of Science and Technology,Speech Communication, vol.50, no.3, pp.215-227, March, 2008. (EURASIP-ISCA Best Paper Award)
Past Publications