Tue, Dec 20 AM 09:25 - 09:30 |
|
- |
|
Tue, Dec 20 AM 09:30 - 10:45 |
(1) |
09:30-09:55 |
|
(2) SP |
09:55-10:20 |
Hard-Attentional Neural Network Models for Emphasis Speech Translation |
Quoc Truong Do, Sakriani Sakti, Graham Neubig, Satoshi Nakamura (NAIST) |
(3) SP |
10:20-10:45 |
Constructing a Japanese multimodal corpus from emotional monologues and dialogues |
Nurul Lubis (NAIST), Randy Gomez (HRI), Sakriani Sakti (NAIST), Keisuke Nakamura (HRI), Koichiro Yoshino, Satoshi Nakamura (NAIST), Kazuhiro Nakadai (HRI) |
|
10:45-10:55 |
Break ( 10 min. ) |
Tue, Dec 20 AM 10:55 - 12:10 |
(4) |
10:55-11:20 |
|
(5) SP |
11:20-11:45 |
Speaker Recognition Based on Features through 1-Dimensional Convolutional Neural Network |
Shohei Sonoda, Yufu Kasahara, Masato Inoue (Waseda Univ) |
(6) SP |
11:45-12:10 |
Study on i-vector based speaker verification using rank for short utterances |
Misaki Tsujikawa (Panasonic/Sokendai), Tsuyoki Nishikawa (Panasonic), Tomoko Matsui (ISM) |
|
12:10-13:10 |
Lunch Break ( 60 min. ) |
Tue, Dec 20 PM 13:10 - 15:10 |
(7) |
13:10-14:10 |
|
(8) |
14:10-15:10 |
|
Tue, Dec 20 PM 15:10 - 16:40 |
(9) SP |
15:10-16:40 |
[Poster Presentation]
Improvement of accent sandhi rules based on accent dictionary for Japanese text-to-speech systems |
Hiroto Aoyama, Takashi Nose, Akinori Ito (Tohoku Univ.) |
(10) SP |
15:10-16:40 |
[Poster Presentation]
F0 control by modeling differential features in DNN-based speech synthesis |
Shuhei Yamada, Takashi Nose, Akinori Ito (Tohoku Univ.) |
(11) SP |
15:10-16:40 |
[Poster Presentation]
Fast algorithm for statistical phrase/accent command estimation based on generative model incorporating spectral features |
Ryotaro Sato (The Univ. of Tokyo), Hirokazu Kameoka, Kunio Kashino (NTT) |
(12) SP |
15:10-16:40 |
[Poster Presentation]
Development of the Julius-compatible interface for the speech recognition engine of Kaldi toolkit |
Yusuke Yamada, Takashi Nose, Yuya Chiba, Akinori Ito (Tohoku Univ.) |
(13) SP |
15:10-16:40 |
[Poster Presentation]
Deep Neural Network Using Fundamental Frequency For Noise Robust Speaker Recognition |
Yoshihiro Suzuki, Yosuke Sugiura, Tetsuya Shimamura (Saitama Univ.) |
(14) SP |
15:10-16:40 |
[Poster Presentation]
Quantization Noise Reduction of Speech by Using Denoising Auto-encoder |
Shohei Oouchi, Kazunori Mano (SIT) |
(15) SP |
15:10-16:40 |
Remote Sensing Applied to the Input Interface of Spoken Dialogue System |
Makoto Koike (MK Microwave Researh) |
(16) |
15:10-16:40 |
|
(17) |
15:10-16:40 |
|
(18) |
15:10-16:40 |
|
(19) |
15:10-16:40 |
|
Tue, Dec 20 PM 16:40 - 17:55 |
(20) SP |
16:40-17:05 |
Generative Adversarial Network-based Postfiltering for Statistical Parametric Speech Synthesis |
Takuhiro Kaneko, Hirokazu Kameoka, Nobukatsu Hojo, Yusuke Ijima, Kaoru Hiramatsu, Kunio Kashino (NTT) |
(21) |
17:05-17:30 |
|
(22) |
17:30-17:55 |
|
Wed, Dec 21 AM 09:20 - 10:35 |
(23) SP |
09:20-09:45 |
Proposal of a robust and high-performance F0 estimator and its evaluation |
Masanori Morise (Univ. of Yamanashi) |
(24) SP |
09:45-10:10 |
Deep Learning-based ASR using Cochleogram and Spectrogram Features Combination |
Andros Tjandra, Sakriani Sakti (NAIST), Mirna Adriani (UI), Satoshi Nakamura (NAIST) |
(25) |
10:10-10:35 |
|
|
10:35-10:45 |
Break ( 10 min. ) |
Wed, Dec 21 AM 10:45 - 11:45 |
(26) SP |
10:45-11:45 |
[Invited Talk]
Towards Fusion of Speech and Natural Language Processing Research
-- Past and Future of Speech Translation Research -- |
Satoshi Nakamura (NAIST) |
|
- |
|
Wed, Dec 21 PM Opening 13:00 - 13:15 |
|
- |
Opening |
Wed, Dec 21 PM 13:15 - 14:45 |
(1) NLC |
13:15-14:45 |
[Poster Presentation]
Design and analysis of dialogue acts for the Kyutech corpus |
Masato Hino, Takasi Yamamura, Kazutaka Shimada (Kyutech) |
(2) NLC |
13:15-14:45 |
[Poster Presentation]
Toward the effective collection of dialogues using gamification |
Shin Kanouchi, Mamoru Komachi (TMU) |
(3) NLC |
13:15-14:45 |
[Poster Presentation]
Constructing taxonomy of implicit information in dialogue by multiple working groups |
Koh Mitsuda, Ryuichiro Higashinaka, Yoshihiro Matsuo (NTT) |
(4) |
13:15-14:45 |
|
(5) |
13:15-14:45 |
|
(6) |
13:15-14:45 |
|
(7) |
13:15-14:45 |
|
(8) |
13:15-14:45 |
|
Wed, Dec 21 PM 14:45 - 16:05 |
(9) NLC |
14:45-15:05 |
[Invited Lecture]
EMNLP 2016 Report (1) |
Kei Wakabayashi (Univ. of Tsukuba) |
(10) NLC |
15:05-15:25 |
[Invited Lecture]
International Conference Report EMNLP 2016 (2) |
Sho Takase (Tohoku Univ.) |
(11) NLC |
15:25-15:45 |
[Invited Lecture]
COLING2016 report (1) |
Shoko Suzuki (IBM Japan) |
(12) NLC |
15:45-16:05 |
[Invited Lecture]
COLING 2016 Report (2) |
Shoko Wakamiya (NAIST) |
|
16:05-16:25 |
Break ( 20 min. ) |
Wed, Dec 21 PM 16:25 - 17:55 |
(13) |
16:25-16:55 |
|
(14) |
16:55-17:25 |
|
(15) |
17:25-17:55 |
|
Thu, Dec 22 AM 09:30 - 10:30 |
(16) NLC |
09:30-10:00 |
AI-based Japanese Short-answer Scoring and Support System |
Tsunenori Ishioka, Masayuki Kameda (NCUEE), Dongyue Louis Liu (GRI) |
(17) NLC |
10:00-10:30 |
An Estimation of Kaomoji's Original Form using Classifiers |
Noriyuki Okumura (NITAC) |
|
10:30-10:45 |
Break ( 15 min. ) |
Thu, Dec 22 AM 10:45 - 11:45 |
(18) |
10:45-11:45 |
Designing Experiments and Reporting Results: Are You Doing It Correctly? |
|
11:45-13:00 |
Lunch Break ( 75 min. ) |
|
13:00-14:00 |
Tour ( 60 min. ) |
Thu, Dec 22 PM 14:00 - 15:30 |
(19) |
14:00-14:30 |
|
(20) |
14:30-15:00 |
|
(21) |
15:00-15:30 |
|
|
15:30-15:45 |
Break ( 15 min. ) |
Thu, Dec 22 PM 15:45 - 17:45 |
(22) |
15:45-16:15 |
|
(23) |
16:15-16:45 |
|
(24) NLC |
16:45-17:15 |
Generating Oracle Sentence by projecting unaligned words from target to source for Machine translation |
Shunsuke Takeno (NUT), Masaaki Nagata (NTT), Kazuhide Yamamoto (NUT) |
(25) NLC |
17:15-17:45 |
Dynamic Social Choice for Pronominal Reference |
Sumiyo Nishiguchi (TUS) |
|
17:45-17:55 |
Closing Adress ( 10 min. ) |