PUBLICATIONS - 2015
Journal
- Keiichiro Oura, ``The State-of-the-art of Singing Voice Synthesis Based on Statistical Model,'' The journal of the Institute of Electronics, Information and Communication Engineers , vol. 98, no. 6, pp. 460-466, 2015. (Review paper) (in Japanese)
link
International Conference
- Kei Sawada, Kei Hashimoto, Keiichiro Oura, and Keiichi Tokuda,
``The NITECH HMM-based text-to-speech system for the Blizzard Challenge 2015,''
Blizzard Challenge 2015 Workshop, Berlin, Germany, September, 2015. (Full paper peer reviewed)
- Siva Reddy Gangireddy, Steve Renals, Yoshihiko Nankaku, and Akinobu Lee, ``Prosodically-Enhanced Recurrent Neural Network Language Models,'' Interspeech 2015, pp. 2390-2394, Dresden, Germany, September, 2015. (Full paper peer reviewed)
- Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``Simultaneous optimization of multiple tree structures for factor analyzed HMM-based speech synthesis,'' Interspeech 2015, pp. 1196-1200, Dresden, Germany, September, 2015. (Full paper peer reviewed)
- Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, and Keiichi Tokuda, ``The effect of neural networks in statistical parametric speech synthesis,'' 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4455-4459, Brisbane, Australia, April, 2015. (Full paper peer reviewed)
- Keiichi Tokuda and Heiga Zen, ``Directly modeling speech waveforms by neural networks for statistical parametric speech synthesis,'' 2015 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), pp. 4215-4219, Brisbane, Australia, April, 2015. (Full paper peer reviewed)
Past Publications