Thu, Nov 8 AM 10:30 - 12:00 |
(1) |
10:30-11:00 |
Effects of speaker adaptive training on arbitrary speaker conversion based on tensor representation |
Daisuke Saito, Nobuaki Minematsu, Keikichi Hirose (Univ. of Tokyo) |
(2) |
11:00-11:30 |
Implementation of real-time statistical voice conversion on a DSP |
Takuto Moriguchi, Tomoki Toda (NAIST), Motoaki Sano, Hiroshi Sato (FOSTER), Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST) |
(3) |
11:30-12:00 |
Intra-speaker spectral parameter variation between utterances of the same sentence and its prediction |
Tatsuo Inukai, Tomoki Toda, Graham Neubig, Sakriani Sakti, Satoshi Nakamura (NAIST) |
|
12:00-13:00 |
Lunch Break ( 60 min. ) |
Thu, Nov 8 PM 13:00 - 14:30 |
(4) |
13:00-13:30 |
Measurement of temporal change of vocal tract volume during production of plosive and fricative consonants |
Tatsuya Kitamura, Hiroaki Hatano (Konan Univ.) |
(5) |
13:30-14:00 |
A study for estimating the length and sectional area of the vocal tract from formants using an acoustic sensitivity function |
Yuki Sakamoto, Tokihiko Kaburagi (Kyushu Univ.) |
(6) |
14:00-14:30 |
Analysis on speaker's intentions conveyed to the listeners by sentence-final particles and their intonations |
Kazuhiko Iwata, Tetsunori Kobayashi (Waseda Univ.) |
|
14:30-14:45 |
Break ( 15 min. ) |
Thu, Nov 8 PM 14:45 - 15:45 |
(7) |
14:45-15:15 |
Improvements of HMM-based speech synthesis using rich context models |
Shinnosuke Takamichi, Tomoki Toda (NAIST), Yoshinori Shiga (NICT), Sakriani Sakti, Graham Neubig, Satoshi Nakamura (NAIST) |
(8) |
15:15-15:45 |
Modeling of local variance of spectral features and its application to parameter generation in HMM-based speech synthesis |
Takashi Nose, Vataya Chunwijitra, Takao Kobayashi (Tokyo Tech) |
|
15:45-16:00 |
Break ( 15 min. ) |
Thu, Nov 8 PM 16:00 - 18:00 |
(9) |
16:00-16:30 |
Prosody Generation based on HMM using Tow-stage Clustering |
Yasuyuki Mitsui, Reishi Kondo, Masanori Kato (NEC) |
(10) |
16:30-17:00 |
One-click vocal tract mapping interface and its applications to signal conversion |
Kohichi Ogata, Kentaro Yamashita (Kumamoto Univ.) |
(11) |
17:00-17:30 |
Three-dimensional rectangular vocal-tract model representing the characteristics of asymmetric vocal-tract wall impedances |
Kunitoshi Motoki (Hokkai-Gakuen Univ.) |
|
- |
|
Fri, Nov 9 AM 09:45 - 10:45 |
(12) |
09:45-10:45 |
[Invited Talk]
Speech synthesis
-- Modeling human-like speech output capabilities -- |
Yoshinori Sagisaka (Waseda Univ.) |
|
10:45-11:00 |
Break ( 15 min. ) |
Fri, Nov 9 AM 11:00 - 12:00 |
(13) |
11:00-12:00 |
[Invited Talk]
Trend of Speech Production Research and its Aspects for Speech Synthesis |
Masaaki Honda (Waseda Univ.) |
|
12:00-13:00 |
Lunch Break ( 60 min. ) |
Fri, Nov 9 PM 13:00 - 16:00 |
|
- |
|