Mon, Dec 20 PM 13:00 - 13:05 |
|
- |
|
Mon, Dec 20 PM 13:05 - 14:20 |
(1) |
13:05-13:30 |
|
(2) |
13:30-13:55 |
|
(3) |
13:55-14:20 |
|
|
14:20-14:35 |
Break ( 15 min. ) |
Mon, Dec 20 PM 14:35 - 16:15 |
(4) NLC |
14:35-15:00 |
Detection of back-channel feedback timings based on consistently tagged spoken dialogue corpus |
Tomohiro Ohno, Yuki Kamiya, Shigeki Matsubara (Nagoya Univ.) |
(5) SP |
15:00-15:25 |
Evaluation of spotting algorithm constrained by keyword co-occurrence for dialogue systems |
Aki Kato, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inst. of Tech.) |
(6) |
15:25-15:50 |
|
(7) SP |
15:50-16:15 |
Trigram dialogue control using POMDPs |
Yasuhiro Minami, Ryuichiro Higashinaka, Kohji Dohsaka, Toyomi Meguro, Akira Mori, Eisaku Maeda (NTT Corp.) |
|
16:15-16:30 |
Break ( 15 min. ) |
Mon, Dec 20 PM 16:30 - 18:10 |
(8) SP |
16:30-16:55 |
Noise suppression method based on noise bias-residual decomposition and optimization |
Masakiyo Fujimoto, Shinji Watanabe, Tomohiro Nakatani (NTT Corp.) |
(9) |
16:55-17:20 |
|
(10) SP |
17:20-17:45 |
Robust Acoustic Modeling Using MLLR Transformation-based Speech Feature Generation |
Arata Itoh, Sunao Hara, Norihide Kitaoka, Kazuya Takeda (Nagoya Univ.) |
(11) SP |
17:45-18:10 |
The Digital Characteristics of Vocal Language
-- The Automata Generated by Digital Signals and Coding Mechanisms -- |
Kimiaki Tokumaru (System Engineer) |
Tue, Dec 21 AM 10:00 - 10:50 |
(12) |
10:00-10:25 |
|
(13) |
10:25-10:50 |
|
|
10:50-11:05 |
Break ( 15 min. ) |
Tue, Dec 21 AM 11:05 - 11:55 |
(14) SP |
11:05-11:30 |
Evaluation of Successive Rapid Hypothesis Determination Algorithm for Continuous Word Recognition |
Hiroyuki Ohno (Nagoya Inst. of Tech.), Hiroshi Kojima (Nagoya Inst. of Tech/Hitachi Solutions, Ltd.), Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda (Nagoya Inst. of Tech.) |
(15) SP |
11:30-11:55 |
Voice Recognition Method Based on Features of Consonant Using Pipelined Matching Circuit |
Jun Nonaka, Keita Okamoto, Hakaru Tamukoh, Masatoshi Sekine (Tokyo Univ. of Agr and Tech.) |
|
11:55-13:00 |
Break ( 65 min. ) |
Tue, Dec 21 PM 13:00 - 13:55 |
(16) |
13:00-13:55 |
[Invited Talk]
Building Watson
-- Can a Computer Compete against the Best Human Contestants in the TV Quiz Show -- |
Hiroshi Kanayama (IBM Japan) |
|
13:55-14:00 |
Break ( 5 min. ) |
Tue, Dec 21 PM 14:00 - 14:55 |
(17) |
14:00-14:55 |
|
|
14:55-15:10 |
Break ( 15 min. ) |
Tue, Dec 21 PM 15:10 - 16:25 |
(18) |
15:10-15:35 |
|
(19) NLC |
15:35-16:00 |
Towards the Domain Independent Why Text Segment Classification by Bag of Grammar and Rule Based Hybrid Model |
Katsuyuki Tanaka, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ) |
(20) |
16:00-16:25 |
|
|
16:25-16:40 |
Break ( 15 min. ) |
Tue, Dec 21 PM 16:40 - 18:10 |
(21) |
16:40-18:10 |
|
(22) NLC |
16:40-18:10 |
Spoken Dialogue Manager Using Partially Observable Markov Decision Processes with Hierarchical Reinforcement Learning |
Yasuhide Kishimoto, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |
(23) |
16:40-18:10 |
|
(24) |
16:40-18:10 |
|
(25) |
16:40-18:10 |
|
(26) |
16:40-18:10 |
|
(27) |
16:40-18:10 |
|
(28) SP |
16:40-18:10 |
A Voice Conversion Method Using Individuality of Sound Source |
Akihito Uemura, Jun Toyama (Hokkaidou Univ.) |
(29) |
16:40-18:10 |
|
(30) |
16:40-18:10 |
|
(31) |
16:40-18:10 |
|
(32) SP |
16:40-18:10 |
Non-negative matrix factorization of segmental STRAIGHT speech spectrograms |
Makoto Koseki, Kazunori Mano (Shibaura Inst. of Tech.) |
(33) SP |
16:40-18:10 |
Study on HMM-based F0 Coding for Very Low Bit-Rate Vocoder |
Takashi Nose, Masashi Kumamoto, Takao Kobayashi (Tokyo Inst. of Tech.) |
(34) SP |
16:40-18:10 |
Iterative basis generation and supervised non-negative matrix factorization for signal analysis |
Toru Nakashika, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.) |