Fiscal year 2011 (Apr. 2011 -- Mar. 2012)

Invited Lecture

  1. Keiichi Tokuda, ``Speech synthesis as a statistical machine learning problem”, 2011 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2011), Hawaii, USA, December 2011.
  2. Steve Renals, ``Towards Natural Speech Technology,’’ IAST: innovation and applications in speech technology, Dublin, March 9 2012.

International Conference

  1. Pablo Martinez Lerin, Daisuke Yamamoto and Naohisa Takahashi, ``Encoding travel traces by using road networks and routing algorithms,’’ Proceedings of the KES IIMSS 2012, Gifu, May 2012. (accepted)
  2. Hiroya Mizutani, Daisuke Yamamoto and Naohisa Takahashi, ``A Fusion of Multiple Focuses on a Focus + Glue + Context Map,’’ Proceedings of the KES IIMSS 2012, Gifu, May 2012. (accepted)
  3. Christophe Veaux ``Voice reconstruction for individuals with vocal disabilities,’’ IAST: innovation and applications in speech technology, Dublin, March 9 2012.
  4. Kei Sawada, Akira Tamamori, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``Face Recognition Based on Separable Lattice 2-D HMMs Using Variational Bayesian Method,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp.2205--2208, Kyoto, Japan, 25-30 Mar. 2012.  
  5. Keisuke Kumaki, Yoshihiko Nankaku, and Keiichi Tokuda, ``Fac Recognition Based on Extended Separable Lattice 2-D HMMs,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp.2209--2212, Kyoto, Japan, 25-30 Mar. 2012.  
  6. Sayaka Shiota, Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda, ``A Model Structure Integration Based on Bayesian Framework for Speech Recognition,'' 2012 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2012), pp.4813--4816, Kyoto, Japan, 25-30 Mar. 2012. 
  7. Keiichiro Oura, Ayami Mase, Yoshihiko Nankaku, and Keiichi Tokuda ``Pich Adaptive Training for HMM-Based Singing Voice Synthesis,'' 2012 IEEE International Conference on Acoustics, Speech, and      Signal Processing (ICASSP 2012), pp.5377--5380, Kyoto, Japan, 25-30 Mar. 2012.