Skip to main content

Publication


Journal Paper

  • Tohru Nagano, Ryuki Tachibana, and Masafumi Nishimura, "Corpus-based Text-to-Speech Front-end for Japanese," IEICE Trans. Information and Systems, J93-D(10):2096-2106, October, 2010 (in Japanese). [Link]
  • Ryuki Tachibana, Tohru Nagano, Gakuto Kurata, Masafumi Nishimura, and Noboru Babaguchi, "Automatic Prosody Labeling Using Multiple Models for Japanese," IEICE Trans. Information and Systems, E90-D(11):1805-1812, November 2007. [Link]

Back to top

International Conference Paper

  • Toru Nakashika, Ryuki Tachibana, Masafumi Nishimura, Tetsuya Takiguchi, and Yasuo Ariki, "Speech Synthesis by Modeling Harmonics Structure with Multiple Function," In Proc. Interspeech, pages 945-948, September 2010.
  • Ryuki Tachibana, Zhiwei Shuang, and Masafumi Nishimura, "Japanese pitch conversion for voice morphing based on differential modeling", In Proc. Interspeech, pages 2651-2654, September, 2009.
  • Slava Shechtman, and Ryuki Tachibana, "Efficient Gradient F0 Tree Model for Prosody Modeling and Unit Selection, Applied for the Embedded US English Concatenative TTS," In Proc. ICASSP 2009, pages 4249-4252, April 2009.
  • Tohru Nagano, Ryuki Tachibana, Nobuyasu Itoh, and Masafumi Nishimura, "Improving Phoneme and Accent Estimation by Leveraging a Dictionary for a Stochastic TTS Front-end," In Proc. ICASSP 2008, pages 4689-4692, April 2008.
  • Ryuki Tachibana, Tohru Nagano, Gakuto Kurata, Masafumi Nishimura, Noboru Babaguchi. "Preliminary Experiments toward Automatic Generation of New TTS Voices from Recorded Speech Alone," In Proc. Interspeech, pages 1917-1920, August 2007.

Back to top

Domestic Conference Paper

  • Masatomo Kobayashi, Reiko Nagatsuma, Ryuki Tachibana, Tohru Nagano, and Hironobu Takagi, "Evaluating Synthesized Audio Descriptions for Online Videos," In Technical Report of IEICE, 2010-WIT-52, volume 109, number 467, pages 21-26, March 2010 (in Japanese).
  • Ryuki Tachibana, Tohru Nagano, Hironobu Takagi, and Masafumi Nishimura, "TTS to Provide Audio Descriptions of Internet Videos," In IPSJ SIG Technical Reports, volume 2010-SLP-80, number 1, pages 1-6, Feburuary 2010.
  • Toru Nakashika, Ryuki Tachibana, Masashi Nishimura, Tetsuya Takiguchi, and Yasuo Ariki, "A study on speech synthesis by modeling harmonics structure with Multi Beta Mixture Model," In Technical Report of IEICE, 2009-NLC/SP-12, pages 165-170, December 2009 (in Japanese).
  • Tohru Nagano, Ryuki Tachibana, Nobuyasu Itoh, and Masafumi Nishimura, "Improving a Stochastic TTS front-end using Accent Class," In Proc. Spring Meeting of Acoustic Society of Japan, pages 38-41, March 2008 (in Japanese).
  • Ryuki Tachibana, Tohru Nagano, and Masafumi Nishimura, "F0 Gradient Model for Acoustic Quality and F0 Consistency of Concatenative TTS," In Technical Report of IEICE, 2007-NLC/SP-12, pages 253-258, December 2007.
  • Ryuki Tachibana, Tohru Nagano, and Masafumi Nishimura, "F0 Modification by Using a Pitch Gradient Model for Concatenative TTS," In Proc. Fall Meeting of Acoustic Society of Japan, pages 327-328, September 2007 (in Japanese).
  • Ryuki Tachibana, Tohru Nagano, Gakuto Kurata, Masafumi Nishimura, and Noboru Babaguchi, "Automatic Accent Labeling Using Multiple Models," In Proc. Spring Meeting of Acoustic Society of Japan, pages 227-228, March 2007 (in Japanese).
  • Tohru Nagano, Ryuki Tachibana, Shinsuke Mori, and Masafumi Nishimura, "An Improvement of a Stochastic-based Front-end for Text-to-Speech System,", In Proc. Spring Meeting of Acoustic Society of Japan, pages 327-328, March 2007 (in Japanese).
  • Ryuki Tachibana, Tohru Nagano, Gakuto Kurata, Masafumi Nishimura, and Noboru Babaguchi, "Automatic Accent Labeling for a Text-to-Speech System," In IPSJ SIG Technical Reports, volume 2007-SLP-5, pages 97-102, Feburuary 2007.
  • Masafumi Nishimura, Ryuki Tachibana, Tohru Nagano, and Gakuto Kurata, "A Study on Totally Trainable TTS System," In Proc. Fall Meeting of Acoustic Society of Japan, pages 237-238, September 2006 (in Japanese).
  • Ryuki Tachibana, and Ryuki Tachibana, "Synthesizing Speech with Emphasis by Learning Prosodic Change," In Proc. Spring Meeting of Acoustic Society of Japan, pages 179-180, March 2005 (in Japanese).

Back to top

Other External Publications

  • Ryuki Tachibana, Tohru Nagano, and Masafumi Nishimura, "Text-to-Speech Synthesis System with an Effective and Easy-to-Use Tuning Interface," IBM ProVision, volume 66, pages 67-73, July 2010 (in Japanese).

Back to top