Sat, Jan 26 PM 13:30 - 15:05 |
(1) |
13:30-14:30 |
[Keynote Address]
Voice Modification for Announcement of Evacuation Guidance in Noisy Reverberant Environments |
Masato Akagi, Masashi Unoki, Rieko Kubo, Maori Kobayashi (JAIST) |
(2) |
14:30-15:05 |
[Invited Lecture]
Measurement method of speech listening performance under various listening environments based on speech and word intelligibility |
Shuichi Sakamoto (Tohoku Univ.) |
|
15:05-15:20 |
Break ( 15 min. ) |
Sat, Jan 26 PM 15:20 - 16:10 |
(3) |
15:20-15:45 |
Acoustical Features of Perceived Urgency in Speech |
Maori Kobayashi, Yasuhiro Hamada, Masato Akagi (JAIST) |
(4) |
15:45-16:10 |
Study on teaching words in disaster prevention broadcast training
-- Announcement to induce evacuation behavior -- |
Yoshio Tsuchida, Sayoko Takano (KIT) |
|
16:10-16:25 |
Break ( 15 min. ) |
Sat, Jan 26 PM 16:25 - 18:00 |
(5) |
16:25-17:25 |
[Fellow Memorial Lecture]
Machine, human and sound communication |
Akinori Ito (Tohoku Univ.) |
|
17:25-17:30 |
Break ( 5 min. ) |
(6) |
17:30-18:00 |
|
Sun, Jan 27 AM 09:00 - 10:00 |
(7) |
09:00-10:00 |
[Tutorial Invited Lecture]
Software components towards end-to-end speech synthesis at NII
-- Tutorial for Tacotron and WaveNet -- |
Yusuke Yasuda, Xin Wang (NII) |
|
10:00-10:15 |
Break ( 15 min. ) |
Sun, Jan 27 AM 10:15 - 11:55 |
(8) |
10:15-10:40 |
A study on End-to-End articulatory-to-speech conversion |
Fumiaki Taguchi, Tokihiko Kaburagi (Kyushu Univ.) |
(9) |
10:40-11:05 |
Evaluation of end-to-end speech synthesis method using speaking styles |
Kiyoshi Kurihara, Nobumasa Seiyama, Tadashi Kumano, Atsushi Imai (NHK) |
(10) |
11:05-11:30 |
A Speaker Recognition Performance Measure based on the Adaptation Quickness and Final Accuracy for Spoken Dialog Systems |
Junko Takami, Takeshi Kawabata (KGU) |
(11) |
11:30-11:55 |
Multimodal Data Augmentation for Visual Speech Recognition using Deep Canonical Correlation Analysis |
Masaki Shimonishi, Satoshi Tamura, Satoru Hayamizu (Gifu University) |