Sat, Jan 20 PM
13:00 - 14:40 |
| (1) |
13:00-13:25 |
An extended log domain pulse model for VOCODERs |
Hideki Kawahara (Wakayama Univ.) |
| (2) |
13:25-13:50 |
A study on statistical speech synthesis based on GP-DNN hybrid model |
Tomoki Koriyama, Takao Kobayashi (Tokyo Tech) |
| (3) |
13:50-14:15 |
DNN Based Voice Conversion Method Considering Outputs of Multiple Networks |
Takuya Fujioka, Sun Qinghua (Hitachi) |
| (4) |
14:15-14:40 |
Searching for the Origin of Natural Language Processing
-- Automata, Telepathy Communication and Schizophrenia -- |
Makoto Koike (MK Microwave) |
| |
14:40-14:55 |
Break ( 15 min. ) |
Sat, Jan 20 PM
14:55 - 16:25 |
| (5) |
14:55-16:25 |
[Poster Presentation]
A study on the articulatory-to-speech conversion by using deep learning |
Fumiaki Taguchi, Tokihiko Kaburagi (Kyushu Univ.) |
| (6) |
14:55-16:25 |
[Poster Presentation]
Automatic speech quality control of English listening materials and examination of Japanese learners’ listening ability in terms of robustness |
Zhang Haoyu, Inoue Yusuke, Saito Daisuke, Minematsu Nobuaki (UTokyo), Yamauchi Yutaka (TIU), Masuda Hinako (SeikeiU) |
| (7) |
14:55-16:25 |
[Poster Presentation]
Influence of frame shift in speech parameters on sound quality by high-quality speech analysis/synthesis system |
Genta Miyashita, Masanori Morise (Yamanashi Univ.) |
| (8) |
14:55-16:25 |
[Poster Presentation]
Analysis of timbre changes caused by expressing fatigue speech |
Takuro Shono, Masanori Morise (Yamanashi Univ.) |
| (9) |
14:55-16:25 |
[Poster Presentation]
TRAJECTORY TRAINING CONSIDERING POWER FOR SPEECH SYNTHESIS BASED ON NEURAL NETWORKS |
Ryohei Funato, Kei Hashimoto, keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) |
Sun, Jan 21 AM
09:30 - 10:30 |
| (10) |
09:30-10:30 |
[Invited Talk]
Investigation of the mechanisms of speech communication by brain science |
Sadao Hiroya (NTT) |
| |
10:30-10:45 |
Break ( 15 min. ) |
Sun, Jan 21 AM
10:45 - 12:25 |
| (11) |
10:45-11:10 |
Perception Boundary of Singleton and Geminate Stops by Japanese and Taiwanese Mandarin Speakers |
Shigeaki Amano (Aichi Shukutoku Univ.), Kimiko Ymakawa (Shokei Univ.) |
| (12) |
11:10-11:35 |
Brain activity during voicing perception in stop consonants
-- A magnetoencephalography study -- |
Shunsuke Tamura, Kazuhito Ito, Naruhito Hironaga, Takako Mitsudo, Nobuyuki Hirose, Shuji Mori (Kyusyu Univ.) |
| (13) |
11:35-12:00 |
Survey on awareness and actual conditions of clumsy speaking |
Tatsuya Kitamura (Konan Univ.), Yukiko Nota (ATR), Michiko Hashi (Prefectural Univ. of Hiroshima), Hironori Takemoto (Chiba Inst. of Technology) |
| (14) |
12:00-12:25 |
Auditory spatial attention affects word intelligibility in noisy environment |
Ryo Teraoka, Shuichi Sakamoto, Zhenglie Cui, Yoiti Suzuki, Satoshi Shioiri (Tohoku Univ.) |
| |
12:25-13:30 |
Lunch Break ( 65 min. ) |
Sun, Jan 21 PM
13:30 - 14:30 |
| (15) |
13:30-14:30 |
[Invited Talk]
Impact of WaveNet on Speech Synthesis Research |
Tomoki Toda (Nagoya Univ./JST) |
| |
14:30-14:45 |
Break ( 15 min. ) |
Sun, Jan 21 PM
14:45 - 16:25 |
| (16) |
14:45-15:10 |
An investigation of multi-speaker WaveNet vocoder |
Tomoki Hayashi, Kazuhiro Kobayashi, Akira Tamamori, Kazuya Takeda, Tomoki Toda (Nagoya Univ.) |
| (17) |
15:10-15:35 |
Statistical voice conversion with WaveNet vocoder |
Kazuhiro Kobayashi, Tomoki Hayashi, Akira Tamamori, Tomoki Toda (Nagoya Univ.) |
| (18) |
15:35-16:00 |
Mel-cepstrum based quantization noise shaping applied to speech synthesis based on WaveNet |
Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda (Nagoya Inst. of Tech.) |
| (19) |
16:00-16:25 |
A study on voice conversion based on WaveNet |
Jumpei Niwa, Takenori Yoshimura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda (NIT) |