===============================================
Technical Committee on Speech (SP)
Chair: Kazunori Mano (Shibaura Inst. of Tech.) Vice Chair: Hiroki Mori (Utsunomiya Univ.)
Secretary: Tetsuya Takiguchi (Kobe Univ.), Masafumi Nishida (Shizuoka Univ.)
Assistant: Taichi Asami (NTT), Kei Hashimoto (Nagoya Inst. of Tech.)
DATE:
Wed, Aug 24, 2016 13:00 - 17:45
Thu, Aug 25, 2016 10:00 - 14:00
PLACE:
Academic Center for Computing and Media Studies, Kyoto University(Yoshida Nihonmatsu-cho, Sakyo-ku, Kyoto-shi, 606-8501, Japan. http://www.media.kyoto-u.ac.jp/accms_en/en/access.html)
TOPICS:
Audio event processing, etc.
----------------------------------------
Wed, Aug 24 PM (13:00 - 13:50)
----------------------------------------
(1) 13:00 - 13:25
Adaptation Methods for Daily Activity Recognition Based on Deep Neural Network
Tomoki Hayashi (Nagoya Univ.), Norihide Kitaoka (Tokushima Univ.), Tomoki Toda, Kazuya Takeda (Nagoya Univ.)
(2) 13:25 - 13:50
Daily Activity Recognition Based on Recurrent Neural Network
Akira Tamamori, Tomoki Hayashi, Tomoki Toda, Kazuya Takeda (Nagoya Univ.)
----- Break ( 10 min. ) -----
----------------------------------------
Wed, Aug 24 PM (14:00 - 16:05)
----------------------------------------
(3) 14:00 - 15:00
[Invited Talk]
Unsupervised Music Understanding based on Hierarchical Bayesian Acoustic and Language Models
Kazuyoshi Yoshii (Kyoto Univ.)
----- Break ( 5 min. ) -----
(4) 15:05 - 16:05
[Invited Talk]
Extension of Array Signal Processing to Asynchronous Distributed Channels
Nobutaka Ono (NII)
----- Break ( 10 min. ) -----
----------------------------------------
Wed, Aug 24 PM (16:15 - 17:45)
----------------------------------------
(5) 16:15 - 17:45
[Poster Presentation]
Kousuke Itakura, Yoshiaki Bando, Eita Nakamura, Katsutoshi Itoyama, Kazuyoshi Yoshii, Tatsuya Kawahara (Kyoto Univ.)
(6) 16:15 - 17:45
[Poster Presentation]
Joint Enhancement of Spectral and Cepstral Sequences of Noisy Speech
Li Li (Univ.Tsukuba), Hirokazu Kameoka, Takuya Higuchi (NTT), Hiroshi Saruwatari (Univ.Tokyo), Shoji Makino (Univ.Tsukuba)
(7) 16:15 - 17:45
(See Japanese page.)
(8) 16:15 - 17:45
[Poster Presentation]
Extraction of brain activity related to auditory impressions induced by HVAC sound using non-negative tensor decomposition
Hajime Yano, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.), Takuya Hotehama (AIST), Masaru Kamiya (DENSO), Seiji Nakagawa (Chiba Univ.)
----------------------------------------
Thu, Aug 25 AM (10:00 - 10:20)
----------------------------------------
----------------------------------------
Thu, Aug 25 AM (10:20 - 11:35)
----------------------------------------
(9) 10:20 - 10:45
Sound collection systems using a crowdsourcing approach for constructing subjective evaluation-based sound maps
Sunao Hara, Shota Kobayashi, Masanobu Abe (Okayama Univ.)
(10) 10:45 - 11:10
Yoshiaki Bando, Katsutoshi Itoyama (Kyoto Univ.), Masashi Konyo, Satoshi Tadokoro (Tohoku Univ.), Kazuhiro Nakadai (Tokyo Tech/HRI-JP), Kazuyoshi Yoshii, Tatsuya Kawahara (Kyoto Univ.), Hiroshi G. Okuno (Waseda Univ.)
(11) 11:10 - 11:35
(See Japanese page.)
----- Lunch ( 70 min. ) -----
----------------------------------------
Thu, Aug 25 PM (12:45 - 14:00)
----------------------------------------
(12) 12:45 - 13:10
Parallel Dictionary Learning for Voice Conversion Using Discriminative Graph-embedded Non-negative Matrix Factorization
Ryo Aihara, Tetsuya Takiguchi, Yasuo Ariki (Kobe Univ.)
(13) 13:10 - 13:35
Pronunciation Error Detection using DNN Articulatory Model based on Transfer Learning
Richeng Duan, Tatsuya Kawahara, Masatake Dantsuji (Kyoto Univ.)
(14) 13:35 - 14:00
Diversity-driven Semi-supervised Ensemble DNN Acoustic Model Training
Sheng Li (Kyoto Univ.), Xugang Lu (NICT), Shinsuke Sakai, Tatsuya Kawahara (Kyoto Univ.)
# Information for speakers
General Talk will have 20 minutes for presentation and 5 minutes for discussion.
Invited Talk will have 50 minutes for presentation and 10 minutes for discussion.
Poster Presentation will have 90 minutes for presentation.
=== Technical Committee on Speech (SP) ===
# FUTURE SCHEDULE:
Thu, Oct 27, 2016 (changed): Shizuoka University. [Thu, Aug 18], Topics: Learning, Recognition, Synthesis, Dialogue, etc.
Last modified: 2016-11-17 15:33:07
|
Notification: Mail addresses are partially hidden against SPAM.
|