Thu, Jun 28 PM
13:00 - 13:50 |
| (1) |
13:00-13:50 |
[Invited Talk]
Active perception and object handling by robots with deep learning |
Tetsuya Ogata (Waseda University/AIST) |
| |
13:50-14:10 |
Break ( 20 min. ) |
Thu, Jun 28 PM
14:10 - 16:10 |
| (2) |
14:10-14:40 |
Language model utilizing image features for automatic speech recognition |
Aiko Hagiwara, Hitoshi Ito, Manon Ichiki, Takeshi Mishima, Shoei Sato (NHK) |
| (3) |
14:40-15:10 |
Study of improving speech intelligibility for glossectomy patients via voice conversion with sound and lip movement. |
Seiya Ogino, Hiroki Murakami, Sunao Hara, Masanobu Abe (Okayama Univ.) |
| (4) |
15:10-15:40 |
Multimodal voice conversion using deep bottleneck features and deep canonical correlation analysis |
Satoshi Tamura, Kento Horio, Hajime Endo, Satoru Hayamizu (Gifu Univ.), Tomoki Toda (Nagoya Univ.) |
| (5) |
15:40-16:10 |
Sound recovery using vibration mode of an object in video |
Yohei Fuse, Yusuke Yasumi, Tetsuya Takiguchi (Kobe Univ.) |
| |
16:10-16:30 |
Break ( 20 min. ) |
Thu, Jun 28 PM
16:30 - 18:00 |
| (6) |
16:30-16:45 |
Analysis of solution diversity about topic model |
Toshio Uchiyama (HIU) |
| (7) |
16:45-17:00 |
|
Saemi Choi (UT), Gloria Zen, Nicu Sebe (UniTrento), Kiyoharu Aizawa (UT) |
| (8) |
17:00-17:15 |
|
|
| |
- |
|
Fri, Jun 29 AM
10:00 - 12:00 |
| (9) |
10:00-10:30 |
Revisiting interference-free power spectral representations of periodic signals |
Hideki Kawahara (Wakayama Univ.), Masanori Morise (Univ. Yamanashi), Kanru Hua (Univ. Illinois) |
| (10) |
10:30-11:00 |
Analysis of speech-to-texture sentiment association characteristics |
Win Thuzar Kyaw, Yoshinori Sagisaka (Waseda Univ.) |
| (11) |
11:00-11:30 |
Speaker adaptation in speech synthesis based on neural networks including temporal structure modeling |
Kento Nakao, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda (NIT) |
| (12) |
11:30-12:00 |
Mapping Acoustic Vector Sequence to Document Vector Based on RNN |
Ryota Nishimura, Miho Higaki, Norihide Kitaoka (Tokushima Univ.) |
| |
12:00-13:00 |
Break ( 60 min. ) |
Fri, Jun 29 PM
13:00 - 13:50 |
| (13) |
13:00-13:50 |
[Invited Talk]
|
Koichi Shinoda (TokyoTech) |
| |
13:50-14:10 |
Break ( 20 min. ) |
Fri, Jun 29 PM
14:10 - 15:10 |
| (14) |
14:10-14:25 |
Discovery of Corresponding Dimensions Between Multiple Multidimensional Sequences
-- Applications and Accelerations of Equivalence Structure Extraction -- |
Seiya Satoh (AIST), Yoshinobu Takahashi (UEC), Hiroshi Yamakawa (Dwango) |
| (15) |
14:25-14:40 |
Symbol Classification and Pitch Recognition in Offline Handwritten Musical Score |
Yuki Hayakawa, Tetsushi Wakabayashi, Yasuji Miyake (Mie Univ.), Wataru Ohyama (Kyushu Univ.) |
| |
- |
|
| |
15:10-15:30 |
Break ( 20 min. ) |
Fri, Jun 29 PM
15:30 - 17:00 |
| (16) |
15:30-17:00 |
|
-or
zer
