===============================================
Technical Committee on Natural Language Understanding and Models of Communication (NLC)
Chair: Hiroshi Kanayama (IBM)
Vice Chair: Takeshi Sakaki (Hottolink), Kazutaka Shimada (Kyushu Inst. of Tech.)
Secretary: Yasuhiko Watanabe (Ryukoku Univ.), Ryuichiro Higashinaka (NTT)
Assistant: Mitsuo Yoshida (Toyohashi Univ. of Tech.), Takeshi Kobayakawa (NICT)
===============================================
Technical Committee on Speech (SP)
Chair: Yoichi Yamashita (Ritsumeikan Univ.) Vice Chair: Hiroki Mori (Utsunomiya Univ.)
Secretary: Masafumi Nishida (Shizuoka Univ.), Hideki Banno (Meijo Univ.)
Assistant: Kei Hashimoto (Nagoya Inst. of Tech.), Satoshi Kobashikawa (NTT)
===============================================
Special Interest Group on Natural Language (IPSJ-NL)
Chair: Kentaro Inui (Tohoku Univ.)
Secretary: Yuki Arase (Osaka Univ.), Naoaki Okazaki (Tokyo Inst. of Tech.), Toshiya Kimura (Mixi Co. Ltd.), Mamoru Komachi (Tokyo Met. Univ.)
===============================================
Special Interest Group on Spoken Language Processing (IPSJ-SLP)
Chair: Nobuaki Minematsu (Univ. Tokyo)
Secretary: Takahiro Shinozaki (Tokyo Inst. of Tech.), Junichi Yamagishi (NII), Takashi Fukuda (IBM Japan)
DATE:
Wed, Dec 20, 2017 10:25 - 18:20
Thu, Dec 21, 2017 09:30 - 18:15
Fri, Dec 22, 2017 10:30 - 15:30
PLACE:
Green Computing Systems Research Organization, Waseda University(27 Waseda-cho, Shinjuku-ku, Tokyo, 162-0042 Japan. https://www.waseda.jp/inst/gcs/access/. Prof. Hideaki Kikuchi)
TOPICS:
The 4th Natural Language Processing Symposium & The 19th Spoken Language Symposium
----------------------------------------
Wed, Dec 20 AM (10:25 - 10:30)
----------------------------------------
----------------------------------------
Wed, Dec 20 AM (10:30 - 12:00)
----------------------------------------
(1) 10:30 - 11:00
(2) 11:00 - 11:30
(3) 11:30 - 12:00
----- Lunch Break ( 90 min. ) -----
----------------------------------------
Wed, Dec 20 PM (13:30 - 15:00)
----------------------------------------
(4) 13:30 - 14:00
(5) 14:00 - 14:30
(6) 14:30 - 15:00
----- Break ( 15 min. ) -----
----------------------------------------
Wed, Dec 20 PM (15:15 - 16:35)
----------------------------------------
(7)/NLC 15:15 - 15:35
[Invited Lecture]
EMNLP2017 Report (1)
Nobuhiro Kaji (Yahoo Japan)
(8)/NLC 15:35 - 15:55
[Invited Lecture]
EMNLP2017 Report (2)
Kazuma Hashimoto (UTokyo)
(9)/NLC 15:55 - 16:15
[Invited Lecture]
IJCNLP 2017 Report (1)
Koh Mitsuda (NTT)
(10)/NLC 16:15 - 16:35
[Invited Lecture]
IJCNLP2017 Report (2)
Yuta Hitomi (Asahi Shimbun)
----- Break ( 15 min. ) -----
----------------------------------------
Wed, Dec 20 PM (16:50 - 18:20)
----------------------------------------
(11) 16:50 - 17:20
(12)/NLC 17:20 - 17:50
Trial of Reinforcement Learning to Analyze Command Utterances for In-vehicle Computer
Masato Tokuhisa, Shuhei Kimura (Tottori Univ.)
(13)/NLC 17:50 - 18:20
Sentiment Analysis with Summarization System using PMI and Pagerank
Haruka Ando (Graduate School of Utsunomiya Univ.), Shin Hara, Shinichi Watanabe (Utsunomiya Univ.)
----------------------------------------
Thu, Dec 21 AM (09:30 - 09:45)
----------------------------------------
----------------------------------------
Thu, Dec 21 AM (09:45 - 10:50)
----------------------------------------
(14)/NLC 09:45 - 10:50
[Poster Presentation]
A Study on the enhancement of system utterances for chat-oriented dialogue systems
Yuiko Tsunomori (NTT DOCOMO), Ryuichiro Higashinaka (NTT), Takeshi Yoshimura, Yoshinori Isoda (NTT DOCOMO)
(15)/NLC 09:45 - 10:50
[Poster Presentation]
Dialogue Act Identification on Kyutech Corpus
Masato Hino, takashi yamamura, kazutaka shimada (Kyutech)
(16)/NLC 09:45 - 10:50
[Poster Presentation]
A Dialogue System with Miscellaneous Knowledge from Sizzle Words
Kazuya Niina, Kazutaka Shimada (KIT)
(17)/NLC 09:45 - 10:50
(See Japanese page.)
(18) 09:45 - 10:50
(19) 09:45 - 10:50
(20) 09:45 - 10:50
(21) 09:45 - 10:50
(22) 09:45 - 10:50
(23) 09:45 - 10:50
(24) 09:45 - 10:50
(25) 09:45 - 10:50
----- Break ( 10 min. ) -----
----------------------------------------
Thu, Dec 21 AM (11:00 - 12:00)
----------------------------------------
(26) 11:00 - 12:00
----- -----
== The 19th Spoken Language Symposium ==
----------------------------------------
Thu, Dec 21 PM Poster presentation (12:50 - 14:20)
----------------------------------------
(1)/SP 12:50 - 14:20
[Poster Presentation]
Selecting Response from Conversational Spoken Dialogue System Based on Distributed Representation of User Utterances
Kengo Ohta (NIT, Anan College), Ryota Nishimura, Norihide Kitaoka (Tokushima Univ.)
(2)/SP 12:50 - 14:20
[Poster Presentation]
Development of Speaker/Environment-Dependent Acoustic Model for Non-Audible Murmur Recognition Based on DNN Adaptation
Seita Noda, Tomoki Hayashi, Tomoki Toda, Kazuya Takeda (Nagoya Univ.)
(3)/SP 12:50 - 14:20
[Poster Presentation]
An Evaluation of Speech Waveform Modification Methods towards Improvement of Speech Intelligibility in Noisy Environment
Tomohiro Takeyama, Kazuhiro Kobayashi, Tomoki Toda, Kazuya Takeda (Nagoya Univ.)
(4)/SP 12:50 - 14:20
[Poster Presentation]
Shota Ikawa (Univ. Tokyo), Kunio Kashino (Univ. Tokyo/NTT)
(5)/SP 12:50 - 14:20
[Poster Presentation]
Realtime analysis and display of voice source periodicity
Hideki Kawahara (Wakayama Univ.), Ken-Ichi Sakakibara (Health Sciences Univ. Hokkaido)
(6)/SP 12:50 - 14:20
Conversational and Eating Behavior Recognition by Leveraging Throat Sound.
Jumpei Ando (Shizuoka Univ.), Takato Saito, Satoshi Kawasaki, Masaji Katagiri, Daizo Ikeda (NTT DOCOMO), Hiroshi Mineno, Tsunakawa Takashi, Masafumi Nishida, Masafumi Nishimura (Shizuoka Univ.)
(7) 12:50 - 14:20
感情音声データベースJTESを用いた感情音声認識におけるモデル適応の性能向上の検討
○相澤 佳孝・小坂 哲夫・加藤 正治(山形大学)・能勢 隆（東北大学）
(8) 12:50 - 14:20
Analyzing the impact of including listener perception annotations in RNN-based emotional speech synthesis
○Jaime Lorenzo-Trueba・Gustav Henter・Shinji Takaki・Junichi Yamagishi (National Institute of Informatics)
(9) 12:50 - 14:20
High-quality nonparallel voice conversion using CycleGAN
○Fuming Fang・Junichi Yamagishi・Isao Echizen (NII)
(10) 12:50 - 14:20
Investigation of Twitter conversation modeling based on Seq2Seq network for DSTC6 task
○Bairong Zhuang・Wenbo Wang・Zhiyu Li・Chonghui Zheng・Takahiro Shinozaki (Tokyo Institute of Technology)
(11) 12:50 - 14:20
英語学習者の発声自動評価を目的としたDNN音声認識システムの検討
○加藤 拓・篠崎 隆宏 (東京工業大学）
(12) 12:50 - 14:20
Joint Learning of Dialog Act Segmentation and Recognition Using Neural Networks
○Tianyu Zhao・Tatsuya Kawahara (Kyoto University)
----- Break ( 15 min. ) -----
----------------------------------------
Thu, Dec 21 PM Organized session: Speech research in AI era (14:35 - 18:15)
----------------------------------------
(13)/SP 14:35 - 15:15
[Invited Talk]
Exploiting redundant coding of message information in machine recognition of speech
Hynek Hermansky (Johns Hopkins Univ.)
(14)/SP 15:15 - 15:55
[Invited Talk]
From Bayes decision rule to sequence-to-sequence processing by neural networks
Hermann Ney (RWTH Aachen Univ.)
----- Break ( 10 min. ) -----
(15) 16:05 - 16:45
[Invited talk] The Role of Prosody in Social AI
○Mari Ostendorf (University of Washington)
(16) 16:45 - 17:25
[Invited talk] Recent advances of exemplar-based sparse representation for voice conversion
○Haizhou Li (National University of Singapore)
(17) 17:25 - 18:15
Panel discussion: Speech research in AI era
Panelists:
Michiel Bacchiani (Google Inc.)
Najim Dehak・Shinji Watanabe (Johns Hopkins University)
Special Guests:
Haizhou Li (National University of Singapore)
Hermann Ney (RWTH Aachen University)
Hynek Hermansky (Johns Hopkins University)
Mari Ostendorf (University of Washington)
Chair:
Satoshi Nakamura (Nara Institute of Science and Technology)
----------------------------------------
Fri, Dec 22 AM (10:30 - 11:45)
----------------------------------------
(18) 10:30 - 10:55
テンソルトレイン分解によるEnd-to-End自動音声認識モデルの圧縮
○森 巧磨・Andros Tjandra・Sakriani Sakti・中村 哲（奈良先端科学技術大学院大学）
(19) 10:55 - 11:20
敵対的学習を適用したEnd-to-end音声認識
○増田 嵩志・齋藤 大輔・峯松 信明 (東京大学)
(20)/SP 11:20 - 11:45
A Sound Source Separation Method for Multiple Person Speech Recognition using Wavelet Analysis Based on Sound Source Position Obtained by Depth Sensor
Nobuhiro Uehara, Kazuo Ikeshiro, Hiroki Imamura (Soka Univ.)
----- Lunch Break ( 75 min. ) -----
----------------------------------------
Fri, Dec 22 PM (13:00 - 14:00)
----------------------------------------
(21)/SP 13:00 - 14:00
[Invited Talk]
Expressive Speech Synthesis: Approaches to Text-to-Speech with Diverse Voices and Styles
Takao Kobayashi (Tokyo Tech.)
----- Break ( 15 min. ) -----
----------------------------------------
Fri, Dec 22 PM (14:15 - 15:30)
----------------------------------------
(22) 14:15 - 14:40
ホルマント平均に基づく声道長比推定法の検討
○坂田 聡・上田 裕市・渡邉 亮(熊本大学)
(23)/SP 14:40 - 15:05
Laughter synthesis considering the context of the utterance in natural conversation
Tomohiro Nagata, Hiroki Mori (Utsunomiya Univ.)
(24) 15:05 - 15:30
日本語インクリメンタル音声合成システム実装のための言語特徴の検討
○柳田 智也・Sakriani Sakti・中村 哲 (奈良先端科学技術大学院大学)
# Information for speakers
General Talk will have 20 minutes for presentation and 5 minutes for discussion.
=== Technical Committee on Natural Language Understanding and Models of Communication (NLC) ===
# FUTURE SCHEDULE:
Fri, Feb 16, 2018 - Sat, Feb 17, 2018: T.O.G. [Mon, Dec 11], Topics: The Twelveth Text Analytics Symposium
=== Technical Committee on Speech (SP) ===
# FUTURE SCHEDULE:
Sat, Jan 20, 2018 - Sun, Jan 21, 2018: The University of Tokyo [Wed, Nov 15]
Mon, Mar 19, 2018 - Tue, Mar 20, 2018: [Mon, Jan 15], Topics: Speech, Engineering/Electro Acoustics, Signal Processing, and Related Topics [SIP, EA, SP]/ Medical Image Engineering, Analysis, Recognition, etc. [MI]
=== Special Interest Group on Natural Language (IPSJ-NL) ===
=== Special Interest Group on Spoken Language Processing (IPSJ-SLP) ===
Last modified: 2017-12-18 11:48:08
|
Notification: Mail addresses are partially hidden against SPAM.
|