Thu, Jul 25 PM 14:10 - 15:40 |
(1) SP |
14:10-14:40 |
Noise reduction based on fragmentary measurement of environmental noise |
Kohei Machida, Akinori Ito (Tohoku Univ.) |
(2) SP |
14:40-15:10 |
Single Channel Dereverberation by Feature Mapping Using Limited Stereo Data |
Aditya Arie Nugraha (Toyohashi Univ. of Tech.), Kazumasa Yamamoto (Toyota Nat. Coll. of Tech./Toyohashi Univ. of Tech.), Seiichi Nakagawa (Toyohashi Univ. of Tech.) |
(3) SP |
15:10-15:40 |
Effectiveness of discriminative approaches for speech recognition under noisy environments on the 2nd CHiME Challenge |
Yuuki Tachioka (Mitsubishi Electric), Shinji Watanabe, Jonathan Le Roux, John R Hershey (MERL) |
Thu, Jul 25 PM 17:30 - 18:00 |
(4) SP |
17:30-18:00 |
Voice conversion using piecewise linear transformation with long-span features and state discrimination of the target speaker |
Jun Ikeshima, Masayuki Suzuki, Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) |
Fri, Jul 26 AM 10:30 - 11:00 |
(5) SP |
10:30-11:00 |
Grapheme-to-phoneme Conversion based on Adaptive Regularization of Weight Vectors |
Keigo Kubo, Sakriani Sakti, Graham Neubig, Tomoki Toda, Satoshi Nakamura (NAIST) |
Fri, Jul 26 AM 11:20 - 11:50 |
(6) SP |
11:20-11:50 |
A Task Development Experiment for the Multi-task Spoken Dialog System based on QA Database |
Shinji Miyake, Akinori Ito (Tohoku Univ.) |
Fri, Jul 26 PM 13:20 - 15:20 |
(7) SP |
13:20-14:20 |
[Invited Talk]
Revisit of speech processing by neural network |
Seiichi Nakagawa (Toyohashi Univ. of Tech.) |
(8) SP |
14:20-15:20 |
[Invited Talk]
An Introduction to Deep Learning
-- Restricted Boltzmann Machine and Pre-Training -- |
Muneki Yasuda (Yamagata Univ.) |
Fri, Jul 26 PM 17:00 - 18:00 |
(9) SP |
17:00-18:00 |
[Invited Talk]
DNN training for automatic speech recognition accelerated by GPU |
Shigeki Matsuda (NICT) |
Sat, Jul 27 AM 09:30 - 10:00 |
(10) SP |
09:30-10:00 |
Analysis of Acoustic Feature of Command Speech Towards a Mobile Robot Under the Robot's Unintended Behavior |
Noriko Totsuka, Akinori Ito (Tohoku Univ.) |
Sat, Jul 27 AM 10:50 - 11:20 |
(11) SP |
10:50-11:20 |
Articulatory Features Based Talking Heads Using Speech Inversion |
Atef Ben-Youssef, Hiroshi Shimodaira, David A. Braude (Univ. of Edinburgh) |