Research
Tomoki Toda is interested in speech and acoustic processing, in particular speech synthesis. His research interests include statistical approaches to speech processing such as voice transformation, speech synthesis, speech production, speech analysis, and speech recognition.
Selected papers
Speech Analysis/Synthesis
- T. Toda, K. Tokuda. Statistical approach to vocal tract transfer function estimation based on factor analyzed trajectory HMM. Proc. ICASSP, pp. 3925-3928, Las Vegas, USA, Apr. 2008.
[Paper]
Voice Conversion Algorithms
- T. Toda, A.W. Black, K. Tokuda. Voice conversion based on maximum likelihood estimation of spectral parameter trajectory. IEEE Transactions on Audio, Speech and Language Processing, Vol. 15, No. 8, pp. 2222-2235, Nov. 2007.
[Paper]
- T. Toda. Eigenvoice-based approach to voice conversion and voice quality control. Proc. NCMMSC, International Symposium, pp. 492-497, Lanzhou, China, Aug. 2009.
[Paper]
- T. Toda, Y. Ohtani, K. Shikano. One-to-many and many-to-one voice conversion based on eigenvoices. Proc. ICASSP, pp. 1249-1252, Hawaii, USA, Apr. 2007.
[Paper]
Statistical Parametric Speech Synthesis
- T. Toda, S. Young. Trajectory training considering global variance for HMM-based speech synthesis. Proc. ICASSP, pp. 4025-4028, Taipei, Taiwan, Apr. 2009.
[Paper]
- T. Toda, K. Tokuda. A Speech parameter generation algorithm considering global variance for HMM-based speech synthesis. IEICE Transactions, Vol. E90-D, No. 5, pp. 816-824, May 2007.
[Paper]
- H. Zen, T. Toda, M. Nakamura, K. Tokuda. Details of the Nitech HMM-based speech synthesis system for the Blizzard Challenge 2005. IEICE Transactions, Vol. E90-D, No. 1, pp. 325-333, Jan. 2007.
[Paper]
Concatenative Speech Synthesis
- T. Toda, H. Kawai, M. Tsuzaki, K. Shikano. An evaluation of cost functions sensitively capturing local degradation of naturalness for segment selection in concatenative speech synthesis. Speech Communication, Vol. 48, No. 1, pp. 45-56, Jan. 2006.
[Paper]
- H. Kawai, T. Toda, J. Ni, M. Tsuzaki, K. Tokuda. XIMERA: a new TTS from ATR based on corpus-based technologies. Proc. 5th ISCA Speech Synthesis Workshop (SSW5), pp. 179-184, Pittsburgh, USA, June 2004.
[Paper]
Body-Conducted Speech Processing
- T. Toda, K. Nakamura, T. Nagai, T. Kaino, Y. Nakajima, K. Shikano. Technologies for processing body-conducted speech detected with non-audible murmur microphone. Proc. INTERSPEECH, pp. 632-635, Brighton, UK, Sep. 2009.
[Paper]
- T. Toda, K. Nakamura, H. Sekimoto, K. Shikano. Voice conversion for various types of body transmitted speech. Proc. ICASSP, pp. 3601-3604, Taipei, Taiwan, Apr. 2009.
[Paper]
- M. Nakagiri, T. Toda, H. Kashioka, K. Shikano. Improving body transmitted unvoiced speech with statistical voice conversion. Proc. INTERSPEECH, pp. 2270-2273, Pittsburgh, USA, Sep. 2006.
[Paper]
Cross-Language Voice Conversion
- M. Charlier, Y. Ohtani, T. Toda, A. Moinet, T. Dutoit. Cross-language voice conversion based on eigenvoices. Proc. INTERSPEECH, pp. 1635-1638, Brighton, UK, Sep. 2009.
[Paper]
- M. Mashimo, T. Toda, H. Kawanami, H. Kashioka, K. Shikano, N. Campbell. Evaluation of cross-language voice conversion using bilingual and non-bilingual databases. Proc. INTERSPEECH, pp. 293-296, Denver, USA, Sep. 2002.
[Paper]
Articulatory-Acoustic Mapping
- T. Toda, A.W. Black, K. Tokuda. Statistical mapping between articulatory movements and acoustic spectrum using a Gaussian mixture model. Speech Communication, Vol. 50, No. 3, pp. 215-227, Mar. 2008.
[Paper]
Softwares
Theses
[Tomoki Toda]