|
- |
|
Mon, Aug 27 AM 11:00 - 11:25 |
(1) |
11:00-11:25 |
Simple method for detecting GCI and GOI based on complex wavelet analysis with cosine series envelope |
Hideki Kawahara (Wakayama Univ.), Ken-Ichi Sakakibara (Health Science Univ. Hokkaido) |
|
11:25-11:35 |
Break ( 10 min. ) |
Mon, Aug 27 AM 11:35 - 13:05 |
(2) |
11:35-13:05 |
|
|
(3) |
11:35-13:05 |
[Poster Presentation]
Question answering system by integration of intention understanding and keyword extraction using attention-based LSTM |
Yuki Matsuyoshi, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
(4) |
11:35-13:05 |
[Poster Presentation]
A Study on Representation of Speaker Information for DNN Speech Synthesis |
Lin Yuhan, Keisuke Imoto, Masahiro Niitsuma, Ryosuke Yamanishi, Yoichi Yamashita (Ritsumeikan Univ.) |
(5) |
11:35-13:05 |
[Poster Presentation]
An Experimental Study on Transforming the Emotion in Speech using GAN |
Kenji Yasuda, Ryohei Orihara, Yuichi Sei, Yasuyuki Tahara, Akihiko Ohsuga (UEC) |
(6) |
11:35-13:05 |
[Poster Presentation]
Discrimination of pharyngeal residue using swallowing sound in dysphagia diagnosis |
Tatsunori Uchino, Atsushi Hashizume, Masahisa Katsuno, Tomoki Toda (Nagoya Univ.) |
|
13:05-14:20 |
Lunch Break ( 75 min. ) |
Mon, Aug 27 PM 14:20 - 15:20 |
(7) |
14:20-15:20 |
[Invited Talk]
Product models and semi-supervised word segmentation |
Daichi Mochihashi (ISM) |
|
15:20-15:30 |
Break ( 10 min. ) |
Mon, Aug 27 PM 15:30 - 16:20 |
(8) |
15:30-15:55 |
Neural Error Corrective Language Models with Multiple Hypotheses |
Tomohiro Tanaka, Ryo Masumura, Yushi Aono (NTT) |
(9) |
15:55-16:20 |
Sound Event Encoder Using Onomatopoeic Representations based on End-to-End Approach |
Koichi Miyazaki, Tomoki Hayashi, Tomoki Toda, Kazuya Takeda (Nagoya Univ.) |
|
16:20-16:30 |
Break ( 10 min. ) |
Mon, Aug 27 PM 16:30 - 17:30 |
(10) |
16:30-17:30 |
[Invited Talk]
Interface Development and Visualization Based on Information Processing for Music and Singing Voices |
Tomoyasu Nakano (AIST) |
Mon, Aug 27 PM 17:30 - 17:50 |
|
- |
|
|
- |
|