研究

研究テーマ

本研究室は，以下の2つのグループから構成されています．

音声対話グループ（駒谷教授，武田助教）

配属希望者向けページを参考にしてください．

オントロジーグループ（古崎准教授）

旧溝口研のページを参考にしてください．

主要発表論文

2016年度

  1. 増田 壮志, 古崎 晃司: 概念階層の比較に基づくオントロジー品質向上支援手法．人工知能学会論文誌，Vol.32, No.2，p.E-G71_1-10，2017．
  2. Ryu Takeda, Kazuhiro Nakadai and Kazunori Komatani: Acoustic Model Training based on Node-wise Weight Boundary Model for Fast and Small-footprint Deep Neural Networks. Computer Speech & Language, 2017. (in press)
  3. Ryu Takeda, Kazunori Komatani: Noise-robust MUSIC-based Sound Source Localization using Steering Vector Transformation for Small Humanoids. Journal of Robotics and Mechatronics, Vol.29, No.1, pp.26-36, 2017.
  4. Ikkyu Aihara, Ryu Takeda, Takeshi Mizumoto, Takuma Otsuka, Hiroshi G. Okuno: Size Effect on Call Properties of Japanese Tree Frogs Revealed by Audio-Processing Technique. Journal of Robotics and Mechatronics, Vol.29, No.1, pp.247-254, 2017.
  5. 杉山 貴昭，船越 孝太郎，中野 幹生，駒谷 和範： 多人数対話におけるユーザの状態に着目したロボットの応答義務の推定．人工知能学会論文誌，Vol.31, No.3，p.C-FB2_1-9，2016．
  6. Ryu Takeda, Kazunori Komatani: Unsupervised Adaptation of Deep Neural Networks for Sound Source Localization using Entropy Minimization. Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.2217-2221, Mar. 7, 2017.
  7. Ryu Takeda, Kazunori Komatani: Discriminative Multiple Sound Source Localization based on Deep Neural Networks using Independent Location Model. Proceedings of IEEE Workshop on Spoken Language Technology (SLT), pp.603-609, Dec. 16, 2016.
  8. Ryu Takeda, Kazunori Komatani: Bayesian Language Model based on Mixture of Segmental Contexts for Spontaneous Utterances with Unexpected Words. Proceedings of International Conference on Computational Linguistics (COLING), pp.161-170, Dec. 13, 2016.
  9. Takahiro Kawamura, Kouji Kozaki, Tatsuya Kushida, Katsutaro Watanabe, Katsuji Matsumura: Expanding Science and Technology Thesauri from Bibliographic Datasets using Word Embedding, The 28th IEEE International Conference on Tools with Artificial Intelligence (ICTAI2016), 8 pages, Nov.8, 2016.
  10. Atsuko Yamaguchi, Kouji Kozaki, Kai Lenz, Yasunori Yamamoto, Hiroshi Masuya, Norio Kobayashi: Semantic Data Acquisition by Traversing Class-Class Relationships over Linked Open Data, Proceedings of the 6th Joint International Semantic Technology (JIST2016),pp.136-151, Nov. 4, 2016.
  11. Takeshi Masuda, Kouji Kozaki, Kazunori Komatani: Ontology Refinement System for Improving Consistency of Classification among Brother Concepts, Workshop and Poster Proceedings of the 6th Joint International Semantic Technology (JIST2016), pp.74-77, Nov. 3, 2016.
  12. Atsuko Yamaguchi, Kouji Kozaki, Kai Lenz, Yasunori Yamamoto, Hiroshi Masuya, Norio Kobayashi: SPARQL Builder: Constructing SPARQL Query by Traversing Class-Class Relationships for Life Science Databases, Workshop and Poster Proceedings of the 6th Joint International Semantic Technology (JIST2016), pp.58-61, Nov. 3, 2016.
  13. Tatsuya Kushida, Takeshi Masuda, Yuka Tateisi, Katsutaro Watanabe, Katsuji Matsumura, Takahiro Kawamura, Kouji Kozaki, Toshihisa Takagi: Refining JST thesaurus and discussing the effectiveness in life science research, Proceedings of International Workshop on Intelligent Exploration of Semantic Data (IESD2016), 12pages, Oct. 8, 2016.
  14. Kohei Ono, Ryu Takeda, Eric Nichols, Mikio Nakano and Kazunori Komatani: Toward Lexical Acquisition during Dialogues through　Implicit Confirmation for Closed-Domain Chatbots. Proceedings of Second Workshop on Chatbots and Conversational Agent Technologies (WOCHAT), Sep. 20, 2016.
  15. Takeshi Imai, Kazuhiko Ohe, Emiko Shinohara, Masayuki Kajino, Ryota Sakurai, Kouji Kozaki, Riichiro Mizoguchi: An Ontological Framework for Representing Topological Information in Human Anatomy, Proceedings of the 7th International Conference on Biomedical Ontology (ICBO 2016), 6pages, Aug. 3, 2016.

2015年度

  1. 古崎 晃司, 來村 徳信, 溝口 理一郎: 生物規範工学オントロジーとLinked Dataに基づくキーワード探索. 人工知能学会論文誌, Vol.31, No.1, p.LOD-D_1-12, 2016.
  2. 山縣 友紀, 古崎 晃司, 今井 健, 大江 和彦, 溝口 理一郎: 疾患知識統合に向けた異常状態オントロジーのLinked Data化. 人工知能学会論文誌, Vol.31, No.1, LOD-A_1-15, 2016.
  3. Riichiro Mizoguchi, Antony Galton, Yoshinobu Kitamura, Kouji Kozaki: Families of roles: A new theory of occurrent-dependent roles. Applied Ontology, Vol.10, No.3-4, pp.367-399, 2015.
  4. Kazunori Komatani, Naoki Hotta, Satoshi Sato, Mikio Nakano: Posteriori Restoration of Turn-Taking and ASR Results for Incorrectly Segmented Utterances. IEICE Transactions on Information and Systems, Vol.E98-D, No.11, pp.1923-1931, 2015.
  5. Ryu Takeda, Kazunori Komatani: Sound Source Localization based on Deep Neural Networks with Directional Activate Function Exploiting Phase Information. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2016), pp.405--409, Mar. 23, 2016.
  6. Kazunori Komatani, Tsugumi Otsuka, Satoshi Sato, Mikio Nakano: Question Selection based on Expected Utility to Acquire Information through Dialogue. International Workshop on Spoken Dialogue Systems (IWSDS2016), 12 pages, Jan. 14, 2016.
  7. Ryu Takeda, Kazuhiro Nakadai, Kazunori Komatani: Acoustic Model Training based on Node-wise Weight Boundary Model Increasing Speed of Discrete Neural Networks. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU 2015), pp.52-58, Dec. 14, 2015.
  8. Ryu Takeda, Kazunori Komatani: Performance Comparison of MUSIC-based Sound Localization Methods on Small Humanoid under Low SNR Conditions. IEEE-RAS International Conference on Humanoid Robots (Humanoids 2015), pp.859--865, Nov. 4, 2015.
  9. Takaaki Sugiyama, Kotaro Funakoshi, Mikio Nakano, Kazunori Komatani: Estimating Response Obligation in Multi-Party Human-Robot Dialogues. IEEE-RAS International Conference on Humanoid Robots (Humanoids 2015), pp.166--172, Nov. 3, 2015.
  10. Kazunori Komatani, Naoki Hotta, Satoshi Sato, Mikio Nakano: User Adaptive Restoration for Incorrectly Segmented Utterances in Spoken Dialogue Systems. 16th Annual SIGDIAL Meeting on Discourse and Dialogue, pp.393--401, Sep. 4, 2015.

2014年度

  1. Naoki Hotta, Kazunori Komatani, Satoshi Sato, Mikio Nakano: Detecting Incorrectly-Segmented Utterances for Posteriori Restoration of Turn-Taking and ASR Results. Interspeech-2014, pp.313-317, Sep. 15, 2014.


Copyright(c) 2016 Prof. Komatani Laboratory. All Rights Reserved.