Wed, Aug 28 PM 13:30 - 14:20 |
(1) |
13:30-13:55 |
WaveCycleGAN2: Neural Waveform Post-Filter For High-Quality Speech Generation |
Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo (NTT) |
(2) |
13:55-14:20 |
Sequence-to-Sequence Voice Conversion Using Context Preservation Mechanism |
Kou Tanaka, Hirokazu Kameoka, Takuhiro Kaneko, Nobukatsu Hojo (NTT) |
|
14:20-14:40 |
Break ( 20 min. ) |
Wed, Aug 28 PM 14:40 - 15:40 |
(3) |
14:40-15:40 |
[Poster Presentation]
Analysis of prosodic differences between a newscaster and amateur speakers using partial-substituted synthetic speech |
Takuya Ozuru (Univ. of Tokyo), Yusuke Ijima (NTT), Daisuke Saito, Nobuaki Minematsu (Univ. of Tokyo) |
(4) |
14:40-15:40 |
[Poster Presentation]
Improvement of generalization performance of non-task-oriented Dialogue System by use of WordNet |
Taisei Aso, Ryoichi Takashima, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
(5) |
14:40-15:40 |
[Poster Presentation]
Intelligibility enhancement based on speech waveform modification using hearing impairment simulator |
Shu Hikosaka, Kazuhiro Kobayashi, Tomoki Hayashi, Shogo Seki, Kazuya Takeda (Nagoya Univ.), Hideki Banno (Meijo Univ.), Tomoki Toda (Nagoya Univ.) |
(6) |
14:40-15:40 |
[Poster Presentation]
An investigation on training of WaveNet vocoder in end-to-end text-to-speech |
Kazuki Yasuhara, Tomoki Hayashi, Tomoki Toda (Nagoya Univ.) |
|
15:40-16:00 |
Break ( 20 min. ) |
Wed, Aug 28 PM 16:00 - 17:25 |
(7) |
16:00-17:00 |
[Invited Talk]
Unsupervised and Few-shot Learning for Anomaly Detection in Sounds |
Yuma Koizumi (NTT) |
(8) |
17:00-17:25 |
Speech Emotion Classification based on Multi-Label Emotion Existence Estimation |
Atsushi Ando, Ryo Masumura, Hosana Kamiyama, Satoshi Kobashikawa, Yushi Aono (NTT) |
Wed, Aug 28 PM 17:25 - 17:45 |
|
- |
|