KATAGIRI Shigeru
Faculty of Science and Engineering Department of Information Systems Design
Professor
Last Updated :2022/11/28

Researcher Profile and Settings

Research Interests

  • 共創情報学
  • 学習理論
  • Co-Creation Informatics
  • Machine Learning

Research Areas

  • Informatics / Sensitivity (kansei) informatics
  • Informatics / Soft computing
  • Informatics / Intelligent robotics
  • Informatics / Perceptual information processing

Research History

  • 1982-1988: Research on rule-based spech recognition
  • 1989- Present: Research on discriminative training including the development of Minimum Classification Error/Generalized Probabilistic Descent method

Research Experience

  • ATR Learning Technology, Outside Director, 2014/06 - Today
  • (株)国際電気通信基礎技術研究所 脳情報解析研究所, 客員研究員, 2013/04 - Today
  • Visiting Researcher (Vice Director), Neural Information Analysis Laboratories, ATR, 2013 - Today
  • Professor, Doshisha University, 2006/04 - Today
  • Doshisha University, Faculty of Science and Engineering, Department of Information Systems Design, 2006 - Today
  • Science Council of Japan, Member, 2006/08 - 2014/07
  • Research Professor, NTT CS Labs, 2006/04 - 2008/03
  • NTT コミュニケーション科学基礎研究所 リサーチプロフェッサー, 2006 - 2008
  • Part-time Lecturer, Faculty of Engineering, Doshsiha University, 2004/04 - 2006/03
  • Nippon Telegraph and Telephone, NTT Communication Laboratories (CS Labs), Director, 2005 - 2006
  • Doshisha University, 2004 - 2006
  • Deputy Director, NTT CS Labs, 2003/04 - 2005/03
  • NTT CS研 副所長 (企画担当), 2003 - 2005
  • Part-time Lecturer, Graduate School of Engieering, Nagoya University, 2001/04 - 2004/03
  • Adjunct Professor, Graduate School of Informatics, Kyoto University, 1998/04 - 2004/03
  • Nagoya University, Graduate School of Engineering, 2001 - 2004
  • NTT CS研 音声オープンラボ統括(兼務), 2000 - 2004
  • Kyoto University, Graduate School of Informatics, 1998 - 2004
  • NTT CS Labs, Intelligent Informatics Laboratory, Executive Manager, 2000/10 - 2003/03
  • NTT CS研, 知能情報研究, 部長, 2000 - 2003
  • NTT CS研 知能情報研究部 知識処理研究グループリーダ(兼務), 2000 - 2001
  • NTT CS研, 知能情報研究部 信号処理研究グループ, グループリーダ, 2000 - 2000
  • NTT CS研, 知能情報研究部 学習理論研究グループ, グループリーダ, 1999 - 2000
  • Group Leader, CS Labs, 1999 - 2000
  • (株)ATR人間情報通信研究所 研究室長, 1997 - 1999
  • Dept. Head, ATR, 1997 - 1999
  • (株)ATR音声翻訳通信研究所 主幹研究員, 1993 - 1997
  • Supervisor, ATR, 1992 - 1997
  • (株)ATR人間情報通信研究所 主幹研究員, 1993 - 1993
  • (株)ATR視聴覚機構研究所 主幹研究員, 1992 - 1993
  • (株)ATR視聴覚機構研究所 主任研究員, 1986 - 1992
  • Senior Researcher, Advanced Telecommunications Research Institute International (ATR), 1986 - 1992
  • AT&T Bell Laboratories, Visiting Researcher, 1989 - 1990
  • 日本電信電話公社(現日本電信電話株式会社(NTT))武蔵野電気通信研究所 研究員, 1982 - 1986
  • Researcher, Nippon Telegraph and Telephone (NTT) Electrical Communication Laboratories, 1982 - 1986

Education

  • Tohoku University, 工学研究科, 情報工学専攻, - 1982
  • Tohoku University, Graduate School, Division of Engineering, - 1982
  • Tohoku University, 工学研究科, 情報工学専攻, - 1979
  • Tohoku University, Graduate School, Division of Engineering, - 1979
  • Tohoku University, Faculty of Engineering, 電気工学科, - 1977
  • Tohoku University, Faculty of Engineering, - 1977

Degree

  • Dr. Engineering, Tohoku University

Association Memberships

  • 電子情報通信学会
  • 日本音響学会
  • ENNS
  • JNNS
  • INNS
  • IEEE
  • Signal and Image Processing
  • European Association for Speech
  • IEICE
  • Acoustical Society of Japan
  • Acoust. Soc. Jpn.
  • ENNS
  • JNNS
  • INNS
  • IEEE
  • Signal and Image Processing
  • European Association for Speech

Committee Memberships

  • 電子情報通信学会「パターン認識・メディア理解」研究会 技術研究報告, 2012 - Today, IEEE, Society, IEEE
  • Member, James L. Flanagan Speech and Audio Processing Award Selection Committee, 2013/07 - 2019/06, IEEE, Society, IEEE
  • Chair, James L. Flanagan Speech and Audio Processing Award Selection Committee, 2016/07 - 2018/06, IEEE, Society
  • Past Chair, Kansai Section, 2013 - 2014, IEEE, Society, IEEE
  • Member, James Flanagan Award Committee, 2013 - 2014, IEEE, Society, IEEE
  • Regional Committee Member, Region 10, 2011 - 2012, IEEE, Society, IEEE
  • Board Member, Japan Council, 2011 - 2012, IEEE, Society, IEEE
  • Chair, Kansai Section, 2011 - 2012, IEEE, Society, IEEE
  • General Co-Chair, MLSP2011, 2010 - 2011, IEEE, Society, IEEE
  • Chair, Kansai Section Nominations Committee, 2009 - 2010, IEEE, Society, IEEE
  • Member, Kansai Section Nominations Committee, 2002 - 2010, IEEE, Society, IEEE
  • Member, James L. Flanagan Speech and Audio Processing Award Selection Committee, 2005/07 - 2009/06, IEEE, Society, IEEE
  • 査読委員, 2007 - 2009, 日本音響学会, Society, 日本音響学会
  • Reviewer, 2007 - 2009, Acoustical Society of Japan, Society, Acoustical Society of Japan
  • Member, Signal Processing Society Nomination & Appointment Committee, 2006 - 2009, IEEE, Society, IEEE
  • Member, James Flanagan Award Committee, 2005 - 2009, IEEE, Society, IEEE
  • Member, Japan Council Award Committee, 2009 - , IEEE, Society, IEEE
  • Member, Japan Council Award Committee, 2009 - , IEEE, Society, IEEE
  • Member, Flank Rosenblatt Award Selection Committee, 2004/07 - 2007/06, IEEE, Society, IEEE
  • 関西支部 会計監査, 2006 - 2007, 日本音響学会, Society, 日本音響学会
  • Member, Flank Rosenblatt Award Committee, 2004 - 2007, IEEE, Society, IEEE
  • 会勢拡大・広報委員会 委員, 2005 - 2006, 日本音響学会, Society, 日本音響学会
  • Member, Organization & Publicity Committee, 2005 - 2006, Acoust. Soc. Jpn., Society, Acoust. Soc. Jpn.
  • 論文誌査読委員, 2001 - 2006, 電子情報通信学会, Society, 電子情報通信学会
  • Action Editor, 2000 - 2006, INNS, JNNS, ENNS, Society, INNS, JNNS, ENNS
  • Action Editor, 2000 - 2006, INNS, JNNS, ENNS, Society, INNS, JNNS, ENNS
  • Member-at-Large, Signal Processing Society Board-of-Governors, 2003 - 2005, IEEE, Society, IEEE
  • Member-at-Large, Signal Processing Society Board-of-Governors, 2003 - 2005, IEEE, Society, IEEE
  • 関西支部 支部長, 2005 - , 日本音響学会, Society, 日本音響学会
  • Chair, Kansai Section, 2005 - , Acoust. Soc. Jpn., Society, Acoust. Soc. Jpn.
  • 会勢拡大・広報委員会 委員, 2001 - 2002, 日本音響学会, Society, 日本音響学会
  • Senior Editor, 2001 - 2002, European Association for Speech, Signal and Image Processing, Society, European Association for Speech, Signal and Image Processing
  • Member, Promotion & Publicity Committee, 2001 - 2002, Acoust. Soc. Jpn., Society, Acoust. Soc. Jpn.
  • Senior Editor, 2001 - 2002, European Association for Speech, Signal and Image Processing, Society, European Association for Speech, Signal and Image Processing
  • 特別企画委員会 委員, 1999 - 2002, 日本音響学会, Society, 日本音響学会
  • Member, Special Event Organizing Committee, 1999 - 2002, Acoust. Soc. Jpn., Society, Acoust. Soc. Jpn.
  • Member, Neural Network Society Administration Committee, 2002 - , IEEE, Society, IEEE
  • Member, Neural Network Society Administration Committee, 2002 - , IEEE, Society, IEEE
  • 関西支部評議員, 1999 - 2001, 日本音響学会, Society, 日本音響学会
  • Councilor, Kansai Section, 1999 - 2001, Acoust. Soc. Jpn., Society, Acoust. Soc. Jpn.
  • Member, Neural Network Council Advisory Committee, 1998 - 2001, IEEE, Society, IEEE
  • Member, Neural Network Council Advisory Committee, 1998 - 2001, IEEE, Society, IEEE
  • 論文誌編集委員, 1997 - 2001, 電子情報通信学会, Society, 電子情報通信学会
  • Member, Signal Processing Society Multi-Media Signal Processing Technical Committee, 1997 - 2001, IEEE, Society, IEEE
  • Transaction Editor, 1997 - 2001, IEICE, Society, IEICE
  • Chair, Signal Processing Society Neural Networks for Signal Processing Technical Committee, 1999 - 2000, IEEE, Society, IEEE
  • Chair, Signal Processing Society Neural Networks for Signal Processing Technical Committee, 1999 - 2000, IEEE, Society, IEEE
  • 代議員, 1999 - , 日本音響学会, Society, 日本音響学会
  • 評議員, 1999 - , 日本音響学会, Society, 日本音響学会
  • Councilor, 1999 - , Acoust. Soc. Jpn., Society, Acoust. Soc. Jpn.
  • Vice Chair, Tokyo Chapter, 1997 - 1998, IEEE, Society, IEEE
  • Secretary, Signal Processing Society Neural Networks for Signal Processing Technical Committee, 1997 - 1998, IEEE, Society, IEEE
  • Vice Chair, Tokyo Chapter, 1997 - 1998, IEEE, Society, IEEE
  • Secretary, Signal Processing Society Neural Networks for Signal Processing Technical Committee, 1997 - 1998, IEEE, Society, IEEE
  • Associate Editor, Trans. on Signal Processing, 1994 - 1997, IEEE, Society, IEEE
  • Associate Editor, Trans. on Signal Processing, 1994 - 1997, IEEE, Society, IEEE
  • Member, Signal Processing Society Neural Networks for Signal Processing Technical Committee, 1991 - 1996, IEEE, Society, IEEE
  • Member, Signal Processing Society Neural Networks for Signal Processing, 1991 - 1996, IEEE, Society, IEEE

Awards

  • NTT R&Dフェロー
    2002, Japan
  • 人工知能学会全国大会ベストプレゼンテーション賞
    2002, Japan
  • NTT R&D Fellow
    2002
  • Best Presentation Award, Japanese Society for Artificial Intelligence
    2002
  • IEEE フェロー
    2001
  • IEEE Fellow
    2001
  • IEEE 信号処理ソサイアティ シニア賞
    1993
  • IEEE Signal Processing Society Senior Award
    1993
  • ATR研究開発表彰特別賞
    1992, Japan
  • ATR R&D Award, Special Prize
    1992
  • ATR研究開発表彰
    1991, Japan
  • ATR R&D Award
    1991
  • 日本音響学会 第27回佐藤論文賞
    1987, Japan
  • 27th Sato Paper Award, Acoustical Society of Japan
    1987
  • 日本音響学会 第22回佐藤論文賞
    1982, Japan
  • 22nd Sato Paper Award, Acoustical Society of Japan
    1982

Published Papers

  • On Speeding-Up by Simplifying Maximum Bayes Boundary-Ness Training
    Kosei Kishishita; Shigeru Katagiri; Miho Ohsaki
    Junior & Student Poster Session, Information・System Society, The Institute of Electronics, Information and Communication Engineers, ISS-SP(015) 149 - 149, 16 Mar. 2022, Research society
  • Experimental Evaluation by Phoneme Recognition of Minimum Classification Error Learning Method with Speech Synthesis Ability as Regularization Condition
    Ukyo Maruyama; Shigeru Katagiri; Miho Ohsaki
    情報・システムソサイエティ特別企画ジュニア&学生ポスターセッション予稿集, The Institute of Electronics, Information and Communication Engineers, ISS-A(57) 55 - 55, 15 Mar. 2022, Research society
  • Experimental Evaluation of Maximum Bayes Boundary-ness Training Method
    Tomohiro Osumi; Shigeru Katagiri; Miho Ohsaki
    The 84th National Convention of Information Processing Society of Japan, Information Processing Society of Japan, (2) 357 - 358, 05 Mar. 2022, Research society
  • Evaluation of Speech Recognition using a KMCE Learning Method for Variable Length Patterns
    Taikichi Koito; Shigeru Katagiri; Miho Ohsaki
    情報処理学会第84回全国大会, Information Processing Society of Japan, (2) 283 - 284, 03 Mar. 2022, Research society
  • An Improved Boundary Uncertainty-Based Estimation for Classifier Evaluation
    David Ha; Shigeru Katagiri; Hideyuki Watanabe; Miho Ohsaki
    Journal of Signal Processing Systems, Springer Science and Business Media LLC, 93(9) 1057 - 1084, Sep. 2021, Scientific journal
  • Evaluation of the Neural-network-based Method to Discover Sets and Representatives of Nonlinearly Dependent Variables
    Miho Ohsaki; Hayato Sasaki; Naoya Kishimoto; Shigeru Katagiri; Kei Ohnishi; Yakub Sebastian; Patrick Then
    2021 5th IEEE International Conference on Cybernetics, CYBCONF 2021, 101 - 106, 08 Jun. 2021, International conference proceedings
  • 音声合成可能性を正則化項とする最小分類誤り学習法の高速化及び実験的評価
    岡内亮太; 片桐滋; 大崎美穂
    電子情報通信学会 情報・システムソサイエティ特別企画 ジュニア&学生ポスターセッション, ISS-P-062, 09 Mar. 2021, Research society
  • 正則化学習を伴う音声認識器の音声合成能力の実験的評価
    大久保拓海; 片桐滋; 大崎美穂
    電子情報通信学会 情報・システムソサイエティ特別企画 ジュニア&学生ポスターセッション, ISS-P-061 135 - 135, 09 Mar. 2021, Research society
  • Experimental Evaluation of Boundary-Uncertainty-Based Classifier Optimization
    Masayuki Kageyama; David Ha; Masahiro Senda; Miho Ohsaki; Shigeru Katagiri
    電子情報通信学会 情報・システムソサイエティ特別企画 ジュニア&学生ポスターセッション, ISS-P-060 134 - 134, 09 Mar. 2021, Research society
  • サポートベクトルにおけるベイズ境界性最大化学習法の検証
    野口大樹; 片桐滋; 大崎美穂
    電子情報通信学会 情報・システムソサイエティ特別企画 ジュニア&学生ポスターセッション, ISS-A-050 49 - 49, 09 Mar. 2021, Research society
  • NNR-GL: A Measure to Detect Co-Nonlinearity Based on Neural Network Regression Regularized by Group Lasso
    Miho Ohsaki; Naoya Kishimoto; Hayato Sasaki; Ryoji Ikeura; Shigeru Katagiri; Kei Ohnishi; Yakub Sebastian; Patrick Then
    IEEE Access, 9 132033 - 132052, 2021, Scientific journal
  • Improved Boundary Uncertainty Estimation for Classifier Selection
    David Ha; Shigeru Katagiri; Miho Ohsaki
    The 7th IEEE MTT-S International Wireless Symposium, Sep. 2020, International conference proceedings
  • 勾配方向ヒストグラム特徴量とマハラノビス距離分類器を用いた医療記録の身体部位図認識
    大崎美穂; 佐々木捷人; 川中普晴; 大西圭(九工大); 片桐滋
    医療情報学, 39(6) 275 - 290, Jun. 2020, Scientific journal
  • CS-ACELPを用いた音声合成可能性を正則化条件とする最小分類誤り学習法の実験的評価
    丸山右京; 梅崎直統; 大久保拓海; 渡辺秀行; 片桐滋; 大崎美穂
    2020年電子情報通信学会総合大会 ISS特別企画「学生ポスターセッション」, ISS-A-056 56 - 56, Mar. 2020, Symposium
  • Study on Maximum Bayes Boundary-ness Training for Pattern Classification
    Masahiro Senda; David Ha; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    IEICE Technical Report, PRMU2019(101) 243 - 248, Mar. 2020, Symposium
  • Experimental Evaluation on Bayes Error Estimation Capability of Kernel Minimum Classification Error Training
    Koji Yamada; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    IEICE Technical Report PRMU, PRMU2019(100) 237 - 242, Mar. 2020, Symposium
  • Experimental Evaluation for Bayes Error Estimation Capability of Large Geometric Margin Minimum Classification Error Training
    Ikuhiko Nishiyama; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    IEICE Technical Report PRMU, PRMU2019(99) 231 - 236, Mar. 2020, Symposium
  • t-Roomにおける人物位置に基づく出力選択を伴う音声サーバの開発
    吉川かいり; 和田理; 片桐滋; 大崎美穂
    2020年電子情報通信学会総合大会 ISS特別企画「学生ポスターセッション」, ISS-A-080 80 - 80, Mar. 2020, Symposium
  • 遺伝的プログラミングと強化学習による自動運転モデルの比較
    山村光平; 中川将輝; 渡辺秀行; 片桐滋; 大崎美穂
    2020年電子情報通信学会総合大会 ISS特別企画「学生ポスターセッション」, ISS-A-062 62 - 62, Mar. 2020, Symposium
  • ボトムアップクラスタリングを用いたベイズ境界の近傍標本の探索
    中村樹生; 蔭山昌幸; 千田将大; 片桐滋; 渡辺秀行; 大崎美穂
    2020年電子情報通信学会総合大会 ISS特別企画「学生ポスターセッション」, ISS-A-055 55 - 55, Mar. 2020, Symposium
  • ベイズ境界性を最大にする新しい学習法の評価
    大角朋弘; 千田将大; 片桐滋; 渡辺秀行; 大崎美穂
    2020年電子情報通信学会総合大会 ISS特別企画「学生ポスターセッション」, ISS-A-054 54 - 54, Mar. 2020, Symposium
  • Study on Generalized Performances of Actor-Critic-Method-based Autonomous Driving Model
    Takeru Nakagawa; Hideyuki Nakagawa; Shigeru Katagiri; Miho Ohsaki
    Proceedings on Information and Systems II, 2020 IEICE General Conference, D-20-8 131 - 131, Mar. 2020, Symposium
  • Minimum Classification Error Training with Speech Synthesis-Based Regularization for Speech Recognition
    Naoto UMEZAKI; Takumi OKUBO; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    ACM, Proc. International Conference on Signal Processing and Machine Learning (SPML2019), Nov. 2019, International conference proceedings
  • Maximum Bayes Boundary-Ness Training for Pattern Classification
    Masahiro SENDA; David HA; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    ACM, Proc. International Conference on Signal Processing and Machine Learning (SPML2019), Nov. 2019, International conference proceedings
  • A Practical Method Based on Bayes Boundary-Ness for Optimal Classifier Parameter Status Selection
    David HA; Yuya TOMOTOSHI; Masahiro SENDA; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    Journal of Signal Processing Systems, 92 135 - 151, May 2019, Scientific journal
  • Analysis of Bayes Error Estimation Capability of Minimum Classification Error Training
    Akihiro Tsuruo; Ikuya Nishiyama; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    IEICE Proc. 2019 General Conference ISS Student Poster Session, ISS-A 48 - 48, Mar. 2019, Symposium
  • Classifier Training Method Maximizing Bayes Boundary-ness
    Masahiro Senda; David Ha; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    IECE Proc. 2019 General Conference ISS Student Poster Session, ISS-A 47 - 47, Mar. 2019, Symposium
  • Study on Kernel Minimum Classification Error Training Method for Time-Series Patterns
    Shun Ogoshi; Koji Yamada; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    IEICE Proc. 2019 General Conference ISS Student Poster Session, ISS-A 46 - 46, Mar. 2019, Symposium
  • Experimental Evaluation of Optimal Classifier Parameter Selection Method Based on Bayes Boundary-ness
    Masayuki Kageyama; David Ha; Yuya Tomoyoshi; Hideyuki Watanabe; Miho Ohsaki; Shigeru Katagiri
    IEICE Proc. 2019 General Conference ISS Student Poster Session, ISS-A 44 - 44, Mar. 2019, Symposium
  • Development of t-Room's Sound Output Control Method Dynamically Selecting Output-Target Monoliths
    Hiroshi Azuma; Osamu Wada; Shigeru Katagiri; Miho Ohsaki
    IPSJ SIG Technical Report, 2019-GN107(10) 1 - 8, Mar. 2019, Symposium
  • Optimal Classifier Parameter Status Selection Based on Bayes Boundary-ness for Multi-ProtoType and Multi-Layer Perceptron Classifiers
    Yuya TOMOTOSHI; David HA; Emilie DELATTRE; Hideyuki WATANABE; Xugang LU; Shigeru KATAGIRI; Miho OHSAKI
    Integrated Uncertaintyin Knowledge Modelling and Decision Making (Lecture Notes in Artificial Intelligence), 11471 295 - 307, Mar. 2019, International conference proceedings
  • Improvement for Boundary-Uncertainty-Based Classifier Parameter Status Selection Method
    David HA; Yuya TOMOTOSHI; Masahiro SENDA; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    IEEE, Proc. Int. Conf. Computational Electromagnetics (ICCEM 2019), Mar. 2019, International conference proceedings
  • Experimental Evaluation of Automatic Determination of Loss Smoothness for Minimum Classification Error Training
    Kazuma Kobayashi; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    IEICE Technical Report PRMU2018-93, 118(362) 97 - 102, Dec. 2018, Symposium
  • Bayes Boundary Estimation Capability Assessment for Large Geometric Margin Minimum Classification Error Training
    Ikuhiko Nishiyama; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    IEICE Technical Report PRMU2018-92, 118(362) 91 - 96, Dec. 2018, Symposium
  • Body Part Diagram Recognition in Medical Records: Application of the Histograms of Oriented Gradients and the Mahalanobis-distance-based Classifier
    Miho OHSAKI; Hayato SASAKI; Hiroharu KAWANAKA; Shigeru KATAGIRI
    Proc. SCIS&ISIS 2018, 1254 - 1259, Dec. 2018, International conference proceedings
  • Discovery of Sets and Representatives of Variables in Co-nonlinear Relationships by Neural Network Regression and Group Lasso
    Miho OHSAKI; Hayato SASAKI; Naoya KISHIMOTO; Shigeru KATAGIRI; Patrick HANG; Hui THEN
    Proc. MABM 2018, 2287 - 2294, Dec. 2018, International conference proceedings
  • Optimality Analysis of Boundary-Uncertainty-Based Classifier Selection Method
    David HA; Hideyuki WATANABE; Yuya TOMOTOSHI; Emilie DELATTRE; Shigeru KATAGIRI
    ACM, Proc. 2018 International Conference on Signal Processing and Machine Learning (SPML2018), 107 - 114, Nov. 2018, International conference proceedings
  • Discovery of Sets and Their Representatives of Co-nonlinear Variables by the Combination of Neural Network Regression and Group Lasso
    Hayato Sasaki; Miho Ohsaki; Shigeru Katagiri
    Proc. FIT 2018, G002, Sep. 2018, Symposium
  • Optimal Classifier Model Status Selection Using Bayes Boundary Uncertainty
    David HA; Emilie DELATTRE; Yuya TOMOTOSHI; Masahiro SENDA; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    IEEE, Proc. Int. Workshop on Machine Learning for Signal Processing (MLSP 2018), 1 - 6, Sep. 2018, International conference proceedings
  • Speaker Adaptation for Multichannel End-to-End Speech Recognition
    Tsubasa OCHIAI; Shinji WATANABE; Shigeru KATAGIRI; Takaaki HORI; John HERSHEY
    IEEE, Proc. International Conf. Acoustics, Speech and Signal Processing (ICASSP 2018), 6707 - 6711, Apr. 2018, International conference proceedings
  • Develpment and Experimental Evaluation of Large Geometric Margin Minimum Classification Error Training for Classification of Variable-length Time Series Patterns
    Tatsuya MATSUHIRO; Tetsuya HASHIMOTO; Mikiyo KITAOKA; David HA; Tsubasa OCHIAI; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    Transaction of Information Processing Society of Japan (IPSJ), 59(4) 1295 - 1308, Apr. 2018, Scientific journal
  • 音声認識における損失関数平滑度自動設定法を伴う大幾何マージン最小分類誤り学習法の効果の分析
    松廣達也; 渡辺秀行; 片桐滋; 大崎美穂
    電子情報通信学会総合大会, ISS-SP-069 184 - 184, Mar. 2018, Symposium
  • 時系列パターンの時間長正規化を伴うカーネル最小分類誤り学習法
    山田浩嗣; 谷陵真; 渡辺秀行; 大崎美穂; 片桐滋
    電子情報通信学会総合大会, ISS-P-026 83 - 83, Mar. 2018, Symposium
  • 線スペクトル対を入力特徴とした最小分類誤り学習法の検討
    梅崎直統; 竹内勇人; 落合翼; 渡辺秀行; 片桐滋; 大崎美穂
    電子情報通信学会総合大会, ISS-P-025 82 - 82, Mar. 2018, Symposium
  • 最小分類誤り学習法における損失関数の平滑度制御による局所解回避効果の検証
    千田将大; 松廣達也; 渡辺秀行; 片桐滋; 大崎美穂
    電子情報通信学会総合大会, ISS-P-024 81 - 81, Mar. 2018, Symposium
  • 自動運転モデルの構築を目指したActor-Critic法の検討
    中川将輝; 八上剛; 渡辺秀行; 片桐滋; 大崎美穂
    電子情報通信学会総合大会, ISS-P-02 80 - 80, Mar. 2018, Symposium
  • 遮音カバー付きスピーカユニットを持つディスプレイのためのメディア伝送サーバの開発
    田中健太郎; 片桐滋; 大崎美穂
    電子情報通信学会総合大会, ISS-A-046 46 - 46, Mar. 2018, Symposium
  • A Classification-Uncertainty-Based Criterion for Classification Boundary Selection
    David HA; Juliette MAES; Yuya TOMOTOSHI; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    IEICE Tech. Report, PRMU2017-166, 121 - 126, Feb. 2018, Symposium
  • Compact kernel classifiers trained with minimum classification error criterion
    Ryoma Tani; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    IEEE International Workshop on Machine Learning for Signal Processing, MLSP, IEEE Computer Society, 2017- 1 - 6, 05 Dec. 2017, International conference proceedings
  • Linux版t-Roomにおける実システム環境を用いた動作確認
    福岡篤志; 和田理; 大崎美穂; 片桐滋
    情報処理学会関西支部大会, G-30, Sep. 2017, Symposium
  • 紙カルテに印刷された身体部位図の認識
    佐々木捷人; 大崎美穂; 川中普晴; 片桐滋
    情報処理学会関西支部大会, G-22, Sep. 2017, Symposium
  • A Class Boundary Selection Criterion for Classification
    David HA; Juliette MAES; Yuya TOMOTOSHI; Charles MELLE; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    IPSJ, Kansai Section Conference, G-11, Sep. 2017, Symposium
  • HOG特徴量とマハラノビス距離に基づく分類器の身体部位図認識への適用
    佐々木捷人; 大崎美穂; 川中普晴; 片桐滋
    第33回ファジィシステムシンポジウム, 273 - 276, Sep. 2017, Symposium
  • 部屋重畳型遠隔コラボレーション支援システムにおける利用者の向きの抽出
    和田理; 大崎美穂; 片桐滋
    情報処理学会電子情報通信学会共催, 情報科学技術フォーラムFIT2017, J008, Sep. 2017, Symposium
  • Does Speech Enhancement Work with End-To-End ASR Objectives?: Experimental Analysis of Multichannnel End-To-End ASR
    Tsubasa Ochiai; Shinji Watanabe; Shigeru Katagiri
    IEEE, Proc. MLSP2017, Sep. 2017, International conference proceedings
  • Confusion-Matrix-Based Kernel Logistic Regression for Imbalanced Data Classification
    Miho Ohsaki; Peng Wang; Kenji Matsuda; Shigeru Katagiri; Hideyuki Watanabe; Anca Ralescu
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, IEEE COMPUTER SOC, 29(9) 1806 - 1819, Sep. 2017, Scientific journal
  • 紙カルテの自動タグ付けを目指した身体部位図認識の検討
    佐々木捷人; 川中普晴; 片桐滋; 大崎美穂
    電子情報通信学会総合大会, ISS-SP-216 216 - 216, Mar. 2017, Symposium
  • 大幾何マージン最小分類誤り学習法の未知標本耐性に関する実験的評価
    塩崎謙; ア・デイビッド; 渡辺秀行; 大崎美穂; 片桐滋
    電子情報通信学会総合大会, ISS-SP-208 208 - 208, Mar. 2017, Symposium
  • 最小分類誤り学習法における損失関数平滑度のクラス共通型自動設定法の実験的評価
    小林和馬; 渡辺秀行; 大崎美穂; 片桐滋
    電子情報通信学会総合大会, ISS-SP-207 207 - 207, Mar. 2017, Symposium
  • ベイズリスク推定を目指す誤分類尺度の分析
    友利宥也; ア・デイビッド; 渡辺秀行; 大崎美穂; 片桐滋
    電子情報通信学会総合大会, ISS-SP-206 206 - 206, Mar. 2017, Symposium
  • NTP を用いる複数Monolith 間同期の実現
    藤田佳樹; 片桐滋; 大崎美穂
    情報処理学会全国大会, 7ZA-07, Mar. 2017, Symposium
  • t-Roomにおける俯瞰カメラを用いた映像出力壁面選択機構の開発
    和田理; 片桐滋; 大崎美穂
    情報処理学会研究報告, 2017-GN-101(28) 1 - 6, Mar. 2017, Symposium
  • 大型ディスプレイ画面上に音像を生成する機能を持つ音声伝送サーバの開発
    片桐 滋松尾雄真; 片桐滋; 大崎美穂
    情報処理学会研究報告, 2017-GN-101(27) 1 - 6, Mar. 2017, Symposium
  • 最小分類誤り基準に基づくサポートベクター再学習による小規模カーネル分類器
    谷陵真; 渡辺秀行; 片桐滋; 大崎美穂
    電子情報通信学会 信学技報 PRMU2016-159, 116(461) 41 - 46, Feb. 2017, Symposium
  • CUMULATIVE MOVING AVERAGED BOTTLENECK SPEAKER VECTORS FOR ONLINE SPEAKER ADAPTATION OF CNN-BASED ACOUSTIC MODELS
    Tsubasa Ochiai; Marc Delcroix; Keisuke Kinoshita; Atsunori Ogawa; Taichi Asami; Shigeru Katagiri; Tomohiro Nakatani
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), IEEE, 5175 - 5179, 2017, International conference proceedings
  • AUTOMATIC NODE SELECTION FOR DEEP NEURAL NETWORKS USING GROUP LASSO REGULARIZATION
    Tsubasa Ochiai; Shigeki Matsuda; Hideyuki Watanabe; Shigeru Katagiri
    2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), IEEE, 5485 - 5489, 2017, International conference proceedings
  • Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers
    Tsubasa Ochiai; Shigeki Matsuda; Hideyuki Watanabe; Xugang Lu; Chiori Hori; Hisashi Kawai; Shigeru Katagiri
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG, E99D(10) 2431 - 2443, Oct. 2016, Scientific journal
  • LGM-MCE Training Based on Parzen Estimation with Sample Weighting
    David HA; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    IPSJ, Kansai Section Conference, G-105 , Sep. 2016, Symposium
  • モデルサイズから見たカーネル最小分類誤り学習法の有用性の検証
    谷陵真; 渡辺秀行; 片桐滋; 大崎美穂
    情報処理学会関西支部大会, C-09, Sep. 2016, Symposium
  • 大幾何マージン最小分類誤り学習法を用いた音声認識に関する実験的評価
    松廣達也; 北岡見生代; ア・デイビッド; 渡辺秀行; 片桐滋; 大崎美穂
    情報処理学会関西支部大会, C-08, Sep. 2016, Symposium
  • Mac OSのためのローカル・ラグ制御機能をもつ音声伝送サーバの実装と性能評価
    松尾雄真; 片桐滋; 大崎美穂
    情報処理学会関西支部大会, C-07, Sep. 2016, Symposium
  • Experimental Analysis of the Behavior of Short Time Series Clustering
    Marta QUEMADA LOPEZ; Miho OHSAKI; Shigeru KATAGIRI
    Technical Report of IPSJ, 2016-BIO-46(35) 1 - 2, Jul. 2016, Symposium
  • Autoencoders with Deformable Templates for Image Reconstruction
    Gregoire SATRE; Tsubasa OCHIAI; Shigeru KATAGIRI; Miho OHSAKI
    IEICE General Conference, ISS-P-117 117 - 117, Mar. 2016, Symposium
  • 音声認識のための大幾何マージン最小分類誤り学習法に関する実験的評価
    松廣達也; 北岡見生代; David Ha; 渡辺秀行; 片桐滋; 大崎美穂
    電子情報通信学会総合大会, ISS-P-114 114 - 114, Mar. 2016, Symposium
  • Model Size Selection for Prototype-Based Classifiers using Large Geometric Margin Minimum Classification Error Training
    David HA; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    IEICE General Conference, ISS-P-110 110 - 110, Mar. 2016, Symposium
  • カーネル最小分類誤り学習法と多クラスサポートベクターマシンの比較実験
    谷陵真; 渡辺秀行; 大崎美穂; 片桐 滋
    電子情報通信学会総合大会, ISS-P-109 109 - 109, Mar. 2016, Symposium
  • 「t-Room」におけるモーフィングに基づく仮想視点映像の生成
    植田耕慈; 和田理; 片桐滋; 大崎美穂
    電子情報通信学会総合大会, ISS-P-102 102 - 102, Mar. 2016, Symposium
  • 偏光フィルタを用いた液晶ディスプレイ前面の映像オブジェクト抽出
    山口達也; 和田理; 大崎美穂; 片桐 滋
    電子情報通信学会総合大会, ISS-P-98 98 - 98, Mar. 2016, Symposium
  • Comparison of Short Time Series Clustering Methods
    Marta QUEMADA LOPEZ; Miho OHSAKI; Shigeru KATAGIRI
    IEICE General Conference, ISS-P-64 64 - 64, Mar. 2016, Symposium
  • 線形変換ネットワークを用いて話者正規化学習されたDNNのためのボトルネック話者適応法の提案
    落合翼; 松田繁樹; 渡辺秀行; Xugang Lu; 河井恒; 片桐滋
    日本音響学会春季研究発表会, 3-P-2 151 - 154, Mar. 2016, Symposium
  • 上下配置型音響反射板を用いる音像生成方式における音像定位精度の調査
    熊谷駿来; 田中健太郎; 原﨑駿; 片桐滋; 大崎美穂
    日本音響学会春季研究発表会, 2-P52 777 - 778, Mar. 2016, Symposium
  • Automobile Driving Support System Evolved by Genetic Programming
    Go Yakami; Ivan Tanev; Katsunori Shimohara; Shigeru Katagiri; Miho Ohsaki
    PROCEEDINGS OF THE 2016 IEEE REGION 10 CONFERENCE (TENCON), IEEE, 255 - 258, 2016, International conference proceedings
  • BOTTLENECK LINEAR TRANSFORMATION NETWORK ADAPTATION FOR SPEAKER ADAPTIVE TRAINING-BASED HYBRID DNN-HMM SPEECH RECOGNIZER
    Tsubasa Ochiai; Shigeki Matsuda; Hideyuki Watanabe; Xugang Lu; Hisashi Kawai; Shigeru Katagiri
    2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS, IEEE, 5015 - 5019, 2016, International conference proceedings
  • 大幾何マージン最小分類誤り学習法におけるプロトタイプ型モデルサイズ自動最適化手法の検討
    荻野将大; 渡辺秀行; 片桐滋; 大崎美穂; Xugang Lu; 河井恒
    電子情報通信学会技術報告 PRMU2015-100, 115(388) 1 - 6, Dec. 2015, Symposium
  • Prediction of Liver Fibrosis Stages in Chronic Hepatitis C Using Kernel Logistic Regression
    Miho OHSAKI; Kenji MATSUDA; Peng WANG; Shigeru KATAGIRI; Hideto YOKOI; Katsuhiko TAKABAYASHI
    Trans. IPSJ, 56(11) 2117 - 2130, Nov. 2015, Scientific journal
  • 空間重畳型遠隔コラボレーション支援システムにおける利用可能領域の拡大
    和田理; 片桐滋; 大崎美穂
    情報処理学会研究報告, 2015-GN-96(22) 1 - 8, Oct. 2015, Symposium
  • 話者正規化学習されたDNNにおける行列のランクに基づく動作分析
    落合翼; 松田繁樹; 渡辺秀行; Xugang Lu; 河井恒; 片桐滋
    日本音響学会秋季研究発表会, 1-Q-3 73 - 76, Sep. 2015, Symposium
  • Kernel Logistic Regression based on the Confusion Matrix for Imbalanced Data Classification
    Peng WANG; Miho OHSAKI; Kenji MATSUDA; Shigeru KATAGIRI; Hideyuki WATANABE
    Technical Report of IPSJ, 2015-BIO-42(55) 1 - 2, Jun. 2015, Symposium
  • SPEAKER ADAPTIVE TRAINING FOR DEEP NEURAL NETWORKS EMBEDDING LINEAR TRANSFORMATION NETWORKS
    Tsubasa Ochiai; Shigeki Matsuda; Hideyuki Watanabe; Xugang Lu; Chiori Hori; Shigeru Katagiri
    2015 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING (ICASSP), IEEE, 4605 - 4609, 2015, International conference proceedings
  • Implementation of Advanced t-Room
    Osamu Wada; Satoshi Ueno; Shigeru Katagiri; Miho Ohsaki
    TENCON 2015 - 2015 IEEE REGION 10 CONFERENCE, IEEE, 2015, International conference proceedings
  • Speech Pattern Classification Using Large Geometric Margin Minimum Classification Error Training
    Mikiyo Kitaoka; Tetsuya Hashimoto; Tsubasa Ochiai; Shigeru Katagiri; Miho Ohsaki; Hideyuki Watanabe; Xugang Lu; Hisashi Kawai
    TENCON 2015 - 2015 IEEE REGION 10 CONFERENCE, IEEE, 2015, International conference proceedings
  • Formulation of the Kernel Logistic Regression based on the Confusion Matrix
    Miho Ohsaki; Kenji Matsuda; Peng Wang; Shigeru Katagiri; Hideyuki Watanabe
    2015 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION (CEC), IEEE, 2327 - 2334, 2015, International conference proceedings
  • A Feature Consisting of Mean, Standard Deviation, and LPC Cepstrum for the Prediction of Liver Fibrosis Stages in Chronic Hepatitis C: Second Report using Optimal Cepstral Order
    Miho Ohsaki; Akifumi Miyazaki; Shigeru Katagiri; Hideto Yokoi; Katsuhiko Takabayashi
    Joint International Conference on Soft Computing and Intelligent Systems and International Symposium on Advanced Intelligent Systems SCIS&ISIS-2014, 1546 - 1549, Dec. 2014
  • Robust and Efficient Pattern Classification using Large Geometric Margin Minimum Classification Error Training
    Hideyuki Watanabe; Tsukasa Ohashi; Shigeru Katagiri; Miho Ohsaki; Shigeki Matsuda; Hideki Kashioka
    JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, SPRINGER, 74(3) 297 - 310, Mar. 2014, Scientific journal
  • Minimum Classification Error Training Incorporating Automatic Loss Smoothness Determination
    Hideyuki Watanabe; Jun'ichi Tokuno; Tsukasa Ohashi; Shigeru Katagiri; Miho Ohsaki; Shigeki Matsuda; Hideki Kashioka
    JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, SPRINGER, 74(3) 311 - 322, Mar. 2014, Scientific journal
  • SPEAKER ADAPTIVE TRAINING USING DEEP NEURAL NETWORKS
    Tsubasa Ochiai; Shigeki Matsuda; Xugang Lu; Chiori Hori; Shigeru Katagiri
    2014 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), IEEE, 6399 - 6403, 2014, International conference proceedings
  • Proposal of the Dynamic Features of Clinical Time Series for the Prediction of Liver Fibrosis Stages in Chronic Hepatitis C
    Ohsaki M; Miyazaki A; Taniguchi E; Katagiri S; Yokoi H; Takabayashi K
    Japan Journal of Medical Informatics, Japan Association for Medical Informatics, 33(2) 79 - 98, Sep. 2013, Scientific journal
  • A Feature Consisting of Mean, Standard Deviation, and LPC Cepstrum for the Prediction of Liver Fibrosis Stages in Chronic Hepatitis C
    Atsufumi MIYAZAKI; Miho OHSAKI; Eri TANIGUCHI; Shigeru KATAGIRI; Hideto YOKOI; Katsuhiko TAKABAYASHI
    Proc. SCIS & ISIS 2012, 2295 - 2298, Nov. 2012, International conference proceedings
  • Application of Kernel Logistic Regression to the Prediction of Liver Fibrosis Stages in Chronic Hepatitis C
    Kenji Matsuda; Miho Ohsaki; Shigeru Katagiri; Hideto Yokoi; Katsuhiko Takabayashi
    6TH INTERNATIONAL CONFERENCE ON SOFT COMPUTING AND INTELLIGENT SYSTEMS, AND THE 13TH INTERNATIONAL SYMPOSIUM ON ADVANCED INTELLIGENT SYSTEMS, IEEE, 780 - 784, 2012, International conference proceedings
  • Feature Extraction for the Prediction of Liver Fibrosis Stages in Chronic Hepatitis C
    Akifumi Miyazaki; Miho Ohsaki; Eri Taniguchi; Shigeru Katagiri; Hideto Yokoi; Katsuhiko Takabayashi
    TENCON 2012 - 2012 IEEE REGION 10 CONFERENCE: SUSTAINABLE DEVELOPMENT THROUGH HUMANITARIAN TECHNOLOGY, IEEE, no. 1569625253 , 2012, International conference proceedings
  • Minimum Classification Error Training Employing Real-Coded Genetic Algorithms
    Kensuke Ota; Shigeru Katagiri; Miho Ohsaki
    TENCON 2012 - 2012 IEEE REGION 10 CONFERENCE: SUSTAINABLE DEVELOPMENT THROUGH HUMANITARIAN TECHNOLOGY, IEEE, no. 1569623985 , 2012, International conference proceedings
  • Comparison between Minimum Classification Error Training and Relevance Vector Machine
    Hisashi Uehara; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    TENCON 2012 - 2012 IEEE REGION 10 CONFERENCE: SUSTAINABLE DEVELOPMENT THROUGH HUMANITARIAN TECHNOLOGY, IEEE, no. 1569623681 , 2012, International conference proceedings
  • Experimental Evaluation of Kernel Minimum Classification Error Training
    Hideaki Tanaka; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    TENCON 2012 - 2012 IEEE REGION 10 CONFERENCE: SUSTAINABLE DEVELOPMENT THROUGH HUMANITARIAN TECHNOLOGY, IEEE, no. 1569622555 , 2012, International conference proceedings
  • Minimum classification error vs. maximum margin: How should we penalize unseen samples?
    Shigeru Katagiri; Hideyuki Watanabe
    2012 3rd International Workshop on Cognitive Information Processing, CIP 2012, 2012, International conference proceedings
  • INCREASING VIRTUAL SAMPLES THROUGH LOSS SMOOTHNESS DETERMINATION IN LARGE GEOMETRIC MARGIN MINIMUM CLASSIFICATION ERROR TRAINING
    Tsukasa Ohashi; Hideyuki Watanabe; Jun'ichi Tokuno; Shigeru Katagiri; Miho Ohsaki; Shigeki Matsuda; Hideki Kashioka
    2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), IEEE, 2081 - 2084, 2012, International conference proceedings
  • Minimum Classification Error Training with Automatic Control of Loss Smoothness
    Jun'ichi TOKUNO; Tsukasa OHASHIO; Hideyuki WATANABE; Shigeru KATAGIRI; Miho OHSAKI
    IEEE, Proc. Region 10 Conference (TENCON2011), Nov. 2011, International conference proceedings
  • 幾何マージンに基づく誤分類尺度を用いた最小分類誤り学習法
    渡辺秀行; 片桐滋; 山田幸太; マクダーモットエリック; 中村篤; 渡部晋治; 大崎美穂
    電子情報通信学会論文誌 D, J94D(10) 1664 - 1675, Oct. 2011, Scientific journal
  • 逐次増加型最小分類誤り学習によるパターン認識
    渡辺秀行; 谷口真一; 片桐滋; 山田幸太; 中村篤; マクダーモットエリック; 渡部晋治; 大崎美穂
    電子情報通信学会論文誌 D, J94D(4) 702 - 711, Apr. 2011, Scientific journal
  • Automatic Loss Smoothness Determination for Minimum Classification Error Training
    Jun'ichi Tokuno; Tsukasa Ohashi; Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    2011 IEEE REGION 10 CONFERENCE TENCON 2011, IEEE, 69 - 73, 2011, International conference proceedings
  • Automatic Loss Smoothness Determination for Large Geometric Margin Minimum Classification Error Training
    Tsukasa Ohashi; Jun'ichi Tokuno; Hideyuki Watanabe; Mastar Project; Shigeru Katagiri; Miho Ohsaki
    2011 IEEE REGION 10 CONFERENCE TENCON 2011, IEEE, 54 - 58, 2011, International conference proceedings
  • MINIMUM CLASSIFICATION ERROR TRAINING WITH GEOMETRIC MARGIN ENHANCEMENT FOR ROBUST PATTERN RECOGNITION
    Hideyuki Watanabe; Shigeru Katagiri; Miho Ohsaki
    2011 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), IEEE, 2011, International conference proceedings
  • MINIMUM CLASSIFICATION ERROR TRAINING WITH AUTOMATIC SETTING OF LOSS SMOOTHNESS
    Hideyuki Watanabe; Jun'ichi Tokuno; Tsukasa Ohashi; Shigeru Katagiri; Miho Ohsaki
    2011 IEEE INTERNATIONAL WORKSHOP ON MACHINE LEARNING FOR SIGNAL PROCESSING (MLSP), IEEE, 2011, International conference proceedings
  • MINIMUM ERROR CLASSIFICATION WITH GEOMETRIC MARGIN CONTROL
    Hideyuki Watanabe; Shigeru Katagiri; Kouta Yamada; Erik McDermott; Atsushi Nakamura; Shinji Watanabe; Miho Ohsaki
    2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, IEEE, 2170 - 2173, 2010, International conference proceedings
  • Toward Large Geometric Margin Minimum Classification Error Training
    Kouta YAMADA; Shigeru KATAGIRI; Erik MCDERMOTT; Hideyuki WATANABE; Atsushi NAKAMURA; Shinji WATANABE; Miho OHSAKI
    The Science and Engineering Review of Doshisha University, 50(3) 43 - 52, Oct. 2009, Research institution
  • Analysis of Subsequence Time-series Clustering Based on Moving Average
    Miho Ohsaki; Masakazu Nakase; Shigeru Katagiri
    2009 9TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING, IEEE, 902 - 907, 2009, International conference proceedings
  • A UNIFIED VIEW FOR DISCRIMINATIVE OBJECTIVE FUNCTIONS BASED ON NEGATIVE EXPONENTIAL OF DIFFERENCE MEASURE BETWEEN STRINGS
    Atsushi Nakamura; Erik McDermott; Shinji Watanabe; Shigeru Katagiri
    2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS, IEEE, 1633 - 1636, 2009, International conference proceedings
  • Clinical Time-series Data Interpolation Based on Regression Diagonosis
    Masakazu Nakase; Miho Ohsaki; Shigeru Katagiri
    Joint International Conference on Soft Computing and Intelligent Systems and International Symposium on Advanced Intelligent Systems SCIS&ISIS-2008, 1859 - 1863, Sep. 2008
  • Clinical Time-series Data Interpolation Based on Regression Diagnosis
    Masakazu NAKASE; Miho OHSAKI; Shigeru KATAGIRI; Yukari HATADA
    SOFT & FCS, Proc. SCIS & ISIS 2008, SU-G1-3 1 - 5, Sep. 2008, International conference proceedings
  • Elaborative Analysis of the Stereo Sound Reproduction Method Using Six Speakers
    Koji NOGUCHI; Aiko KUNIKAMI; Maiko SUGAWARA; Aki TSUTSUI; Shigeru KATAGIRI; Miho OHSAKI; Masato MIYOSHI
    AES, Proc. Japan Section Conference, 1 1 - 12, Jul. 2008, International conference proceedings
  • Re-evaluation of the stereo reproduction method using six speakers for media space development
    Koji Noguchi; Aiko Kunikami; Maiko Sugawara; Aki Tsutsui; Shigeru Katagiri; Miho Ohsaki; Masato Miyoshi
    2008 INTERNATIONAL CONFERENCE ON AUDIO, LANGUAGE AND IMAGE PROCESSING, VOLS 1 AND 2, PROCEEDINGS, IEEE, 2 225 - 231, 2008, International conference proceedings
  • Inverting mappings from smooth paths through R-n to paths through R-m: A technique applied to recovering articulation from acoustics
    John Hogden; Philip Rubin; Erik McDermott; Shigeru Katagiri; Louis Goldstein
    SPEECH COMMUNICATION, ELSEVIER SCIENCE BV, 49(5) 361 - 383, May 2007, Scientific journal
  • Discriminative training for large-vocabulary speech recognition using minimum classification error
    Erik McDermott; Timothy J. Hazen; Jonathan Le Roux; Atsushi Nakamura; Shigeru Katagiri
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 15(1) 203 - 223, Jan. 2007, Scientific journal
  • Dynamic assignment of Gaussian components in modelling speech spectra
    Parham Zolfaghari; Hiroko Kato; Yasuhiro Minami; Atsushi Nakamura; Shigeru Katagiri; Roy Patterson
    Journal of VLSI Signal Processing Systems for Signal, Image, and Video Technology, 45(1-2) 7 - 19, Nov. 2006, International conference proceedings
  • Dynamic assignment of Gaussian components in modelling speech spectra
    Parham Zolfaghari; Hiroko Kato; Yasuhiro Minami; Atsushi Nakamura; Shigeru Katagiri; Roy Patterson
    JOURNAL OF VLSI SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, SPRINGER, 45(1-2) 7 - 19, Nov. 2006, Scientific journal
  • Discriminative training via minimization of risk estimates based on Parzen smoothing
    Erik McDermott; Shigeru Katagiri
    APPLIED INTELLIGENCE, SPRINGER, 25(1) 37 - 57, Aug. 2006, Scientific journal
  • A new kernel-based formalization of minimum error pattern recognition
    Erik McDermott; Shigeru Katagiri
    Handbook of Pattern Recognition and Computer Vision, 3rd Edition, World Scientific Publishing Co., 41 - 54, 01 Jan. 2005, In book
  • Minimum classification error for large scale speech recognition tasks using weighted finite state transducers
    E McDermott; S Katagiri
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5, IEEE, 1 113 - 116, 2005, International conference proceedings
  • A Theoretical Analysis of Speech Recognition Based on Feature Trajectory Models
    Y. Minami; E. McDermott; A. Nakamura; S. Katagiri
    ICSLP, I 549 - 552, Oct. 2004, International conference proceedings
  • A derivation of minimum classification error from the theoretical classification risk using Parzen estimation
    E McDermott; S Katagiri
    COMPUTER SPEECH AND LANGUAGE, ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD, 18(2) 107 - 122, Apr. 2004, Scientific journal
  • Recognition Method with Parametric Trajectory Synthesized Using Hmms
    Y. Minami; E. McDermott; A. Nakamura; S. Katagiri
    SWIM, 776 - 786, Jan. 2004, International conference proceedings
  • Model selection for mixture of Gaussian based spectral modelling
    P Zolfaghari; H Kato; Y Minami; A Nakamura; S Katagiri
    MACHINE LEARNING FOR SIGNAL PROCESSING XIV, IEEE, 325 - 334, 2004, International conference proceedings
  • Bayesian modelling of the speech spectrum using mixture of Gaussians
    P Zolfaghari; S Watanabe; A Nakamura; S Katagiri
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS, IEEE, 1 553 - 556, 2004, International conference proceedings
  • Blind Inversion of Multidimensional Functions for Speech Enhancement
    John HOGDEN; Patrick F. VALDEZ; Shigeru KATAGIRI; Erik MCDERMOTT
    Proc. Eurospeech2003, 1409 - 1412, Sep. 2003, International conference proceedings
  • Longitudinal-Observation-Based Quantitative Analysis of Vocabulary and Sentence Aquisition
    Toshiro INUI; Shigeaki AMANO; Kimihisa KONDO; Shigeru KATAGIRI
    Congnitive Science, 10(2) 304 - 317, Jun. 2003, Scientific journal
  • A new formalization of minimum classification error using a Parzen estimate of classification chance
    E McDermott; S Katagiri
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL II, PROCEEDINGS, IEEE, 2 713 - 716, 2003, International conference proceedings
  • Deriving disambiguous queries in a spoken interactive ODQA system
    C Hori; T Hori; H Isozaki; E Maeda; S Katagiri; S Furui
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS, IEEE, 1 624 - 627, 2003, International conference proceedings
  • Pervasive unsupervised adaptation for lecture speech transcription
    D Willett; T Niesler; E McDermott; Y Minami; S Katagiri
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS, IEEE, 1 292 - 295, 2003, International conference proceedings
  • Recognition method with parametric trajectory generated from mixture distribution HMMs
    Y Minami; E McDermott; A Nakamura; S Katagiri
    2003 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS, IEEE, 1 124 - 127, 2003, International conference proceedings
  • A Parzen Window Based Derivation of Minimum Classification Error from the Theoretical Bayes Classification Risk
    Erik MCDERMOTT; Shigeru KATAGIRI
    IEEE, Proc. ICASSP2002, 2465 - 2468, Sep. 2002, International conference proceedings
  • Unsupervised Pronunciation Adaptation for Off-line Transcription of Japanese Lecture Speeches
    Daniel WILLETT; Erik MCDERMOTT; Shigeru KATAGIRI
    ISCA, Proc. Tutorial and Research Workshop -Pronunciation Modeling and Lexicon Adaptation for Spoken Language (PMLA), 36 - 41, Sep. 2002, International conference proceedings
  • Guest editorial special issue on intelligent multimedia processing
    Ling Guan; Tülay Adali; Shigeru Katagiri; Jan Larsen; Jose Principe
    IEEE Transactions on Neural Networks, 13(4) 789 - 792, Jul. 2002, Scientific journal
  • Effect of native language on the production of second-language speech segments
    Ryo Komaki; Reiko Akahane-Yamada; Shigeru Katagiri
    Acoustical Science and Technology, 23(3) 163 - 165, May 2002, Scientific journal
  • Minimum classification error via a Parzen window based estimate of the theoretical Bayes classification risk
    E McDermott; S Katagiri
    NEURAL NETWORKS FOR SIGNAL PROCESSING XII, PROCEEDINGS, IEEE, 415 - 424, 2002, International conference proceedings
  • A recognition method with parametric trajectory synthesized using direct relations between static and dynamic feature vector time series
    Y Minami; E McDermott; A Nakamura; S Katagiri
    2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, IEEE, 1 957 - 960, 2002, International conference proceedings
  • Recent advances in efficient decoding combining on-line transducer composition and smoothed language model incorporation
    D Willett; S Katagiri
    2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, IEEE, 1 713 - 716, 2002, International conference proceedings
  • A new approach to designing a feature extractor in speaker identification based on discriminative feature extraction
    C Miyajima; H Watanabe; K Tokuda; T Kitamura; S Katagiri
    SPEECH COMMUNICATION, ELSEVIER SCIENCE BV, 35(3-4) 203 - 218, Oct. 2001, Scientific journal
  • A Recognition Method Using Synthesis-Based Scoring That Incorporates Direct Relations Between Static and Dynamic Feature Vector Time Series
    Yasuhiro MIMAMI; Erik MCDERMOTT; Atsushi NAKAMURA; Shigeru KATAGIRI
    Proc. Workshop for Consistent & Reliable Acoustic Cues for Sound Analysis (CRAC2001), 1 - 4, Sep. 2001, International conference proceedings
  • Time and Memory Efficient Viterbi Decoding for LVCSR using a Precompiled Search Network
    Daniel WILLETT; Erik MCDERMOTT; Yasuhiro MINAMI; Shigeru KATAGIRI
    Proc. Eurospeech 2001, 2 847 - 850, Sep. 2001, International conference proceedings
  • An application of discriminative feature extraction lo filter-bank-based speech recognition
    A Biem; S Katagiri; E McDermott; BH Juang
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 9(2) 96 - 110, Feb. 2001, Scientific journal
  • Smoothed language model incorporation for efficient time-synchronous beam search decoding in LVCSR
    D Willett; E McDermott; S Katagiri
    ASRU 2001: IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING, CONFERENCE PROCEEDINGS, IEEE, 178 - 181, 2001, International conference proceedings
  • Law Discovery from Financial Data using Neural Networks
    Kazumi SAITO; Naonori UEDA; Shigeru KATAGIRI; Yutaka FUKAI; Hiroshi FUJIMARU; Masayuki FUJINAWA
    IEEE/IAFE/INFORMS, Proc. CIFEr2000, 209 - 212, Mar. 2000, International conference proceedings
  • Discriminative training for large vocabulary telephone-based name recognition
    E McDermott; A Biem; S Tenpaku; S Katagiri
    2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI, IEEE, 6 3739 - 3742, 2000, International conference proceedings
  • Speaker Recognition Based on Discriminative Feature Extraction - Optimization of Mel-Cepstral Features Using Second-Order All-Pass Warping Function
    Chiyomi MIYAJIMA; Hideyuki WATANABE; Keiichi TOKUDA; Tadashi KITAMURA; Shigeru KATAGIRI
    Proc. Eurospeech99, 2 779 - 782, Sep. 1999, International conference proceedings
  • A new approach to acoustic signal monitoring based on the generalized probabilistic descent method
    H Watanabe; Y Matsumoto; S Tanaka; S Katagiri
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 47(9) 2615 - 2618, Sep. 1999, Scientific journal
  • Separation of an Overlapped Signal Using Speech Production Models
    Hideyuki WATANABE; Satoru FUJITA; Shigeru KATAGIRI
    IEEE, Neural Networks for Signal Processing IX, 293 - 302, Aug. 1999, International conference proceedings
  • Pattern recognition using a family of design algorithms based upon the generalized probabilistic descent method
    S Katagiri; BH Juang; CH Lee
    PROCEEDINGS OF THE IEEE, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 86(11) 2345 - 2373, Nov. 1998, Scientific journal
  • Sound monitoring based on the Generalized Probabilistic Descent method
    H Watanabe; Y Matsumoto; S Tanaka; S Katagiri
    NEURAL NETWORKS FOR SIGNAL PROCESSING VIII, IEEE, 383 - 392, 1998, International conference proceedings
  • Minimum Detection Error training for acoustic signal monitoring
    H Watanabe; Y Matsumoto; S Katagiri
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, IEEE, 2 1193 - 1196, 1998, International conference proceedings
  • Subspace method for minimum error pattern recognition
    H Watanabe; S Katagiri
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, IEICE-INST ELECTRONICS INFORMATION COMMUNICATIONS ENG, E80D(12) 1195 - 1204, Dec. 1997, Scientific journal
  • Discriminative metric design for robust pattern recognition
    H Watanabe; T Yamaguchi; S Katagiri
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 45(11) 2655 - 2662, Nov. 1997, Scientific journal
  • String-Level MCE for Continuous Phoneme Recognition
    Erik MCDERMOTT; Shigeru KATAGIRI
    Proc. Eurospeech97, 1 123 - 126, Sep. 1997, International conference proceedings
  • Pattern recognition using discriminative feature extraction
    A Biem; S Katagiri; BH Juang
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 45(2) 500 - 504, Feb. 1997, Scientific journal
  • Efficient normalization based upon GPD
    E Woudenberg; A Biem; E McDermott; S Katagiri
    1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V, I E E E, COMPUTER SOC PRESS, 4 3245 - 3248, 1997, International conference proceedings
  • HMM speech recognizer based on discriminative metric design
    H Watanabe; S Katagiri
    1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V, I E E E, COMPUTER SOC PRESS, 4 3237 - 3240, 1997, International conference proceedings
  • Cepstrum-based filter-bank design using discriminative feature extraction training at various levels
    A Biem; S Katagiri
    1997 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I - V, I E E E, COMPUTER SOC PRESS, 2 1503 - 1506, 1997, International conference proceedings
  • Neural Networks for Pattern Recognition
    Shigeru KATAGIRI
    Proc. 1996 Invited Workshop on Pattern Recognition for Multimedia Techniques, 5 - 20, Oct. 1996, International conference proceedings
  • Toward a unified design of pattern recognizers
    H Watanabe; A Biem; S Katagiri
    NEURAL NETWORKS FOR SIGNAL PROCESSING VI, I E E E, 283 - 292, 1996, International conference proceedings
  • Discriminative feature extraction application to filter bank design
    A Biem; E McDermott; S Katagiri
    NEURAL NETWORKS FOR SIGNAL PROCESSING VI, I E E E, 273 - 282, 1996, International conference proceedings
  • A telephone-based directory assistance system adaptively trained using minimum classification error generalized probabilistic descent
    E McDermott; EA Woudenberg; S Katagiri
    1996 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, CONFERENCE PROCEEDINGS, VOLS 1-6, I E E E, 6 3346 - 3349, 1996, International conference proceedings
  • A Discriminative Filter Bank Model for Speech Recognition
    Alain BIEM; Erik MCDERMOTT; Shigeru KATAGIRI
    Proc. Eurospeech95, 545 - 548, Sep. 1995, International conference proceedings
  • Discriminative Subspace Method for Minimum Error Pattern Recognition
    Hideyuki WATANABE; Shigeru KATAGIRI
    IEEE, Neural Networks for Signal Processing V, 77 - 86, Sep. 1995, International conference proceedings
  • A Novel Approach to Pattern Recognition Based on Discriminative Metric Design
    Hideyuki WATANABE; Tsuyoshi YAMAGUCHI; Shigeru KATAGIRI
    IEEE, Neural Networks for Signal Processing V, 48 - 57, Aug. 1995, International conference proceedings
  • A MINIMUM ERROR APPROACH TO SPOTTING-BASED PATTERN-RECOGNITION
    T KOMORI; S KATAGIRI
    IEICE TRANSACTIONS ON INFORMATION AND SYSTEMS, IEICE-INST ELECTRON INFO COMMUN ENG, E78D(8) 1032 - 1043, Aug. 1995, Scientific journal
  • DISCRIMINATIVE METRIC DESIGN FOR PATTERN RECOGNITION
    H WATANABE; T YAMAGUCHI; S KATAGIRI
    1995 INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING - CONFERENCE PROCEEDINGS, VOLS 1-5, I E E E, 5 3439 - 3442, 1995, International conference proceedings
  • A novel spotting-based approach to continuous speech recognition: Minimum error classification of keyword-sequences
    Takashi Komori; Shigeru Katagiri
    Journal of the Acoustical Society of Japan (E) (English translation of Nippon Onkyo Gakkaishi), 16(3) 147 - 157, 1995, Scientific journal
  • A Unified Approach to Pattern Recognition
    Shigeru KATAGIRI
    Proc. 1994 Int. Symp. Artificial Neural Networks, 561 - 570, Dec. 1994, International conference proceedings
  • PROTOTYPE-BASED MINIMUM CLASSIFICATION ERROR GENERALIZED PROBABILISTIC DESCENT TRAINING FOR VARIOUS SPEECH UNITS
    E MCDERMOTT; S KATAGIRI
    COMPUTER SPEECH AND LANGUAGE, ACADEMIC PRESS LTD- ELSEVIER SCIENCE LTD, 8(4) 351 - 368, Oct. 1994, Scientific journal
  • A Novel Fuzzy Partition Model Architecture for Classifying Dynamic Patterns
    Yoshinaga KATO; Shigeru KATAGIRI
    Proc. ICSLP94, 1551 - 1554, Sep. 1994, International conference proceedings
  • Minimum Error Classification of Keyword-Sequences
    Takashi KOMORI; Shigeru KATAGIRI
    IEEE, Neural Networks for Signal Processing IV, 352 - 361, Sep. 1994, International conference proceedings
  • Minimum Error Training for Speech Recognition
    Erik MCDERMOTT; Shigeru KATAGIRI
    IEEE, Neural Networks for Signal Processing IV, 259 - 268, Sep. 1994, International conference proceedings
  • PROTOTYPE-BASED MINIMUM ERROR TRAINING FOR SPEECH RECOGNITION
    E MCDERMOTT; S KATAGIRI
    APPLIED INTELLIGENCE, SPRINGER, 4(3) 245 - 256, Jul. 1994, Scientific journal
  • FILTER BANK DESIGN BASED ON DISCRIMINATIVE FEATURE EXTRACTION
    A BIEM; S KATAGIRI
    ICASSP-94 - PROCEEDINGS, VOL 1, I E E E, 1 485 - 488, 1994, International conference proceedings
  • A New Hybrid Algorithm for Speech Recognition Based on HMM Segmentation and Learning Vector Quantization
    Shigeru Katagiri; Chin-Hui Lee
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 1(4) 421 - 430, Oct. 1993, Scientific journal
  • Discriminative Feature Extraction for Speech Recognition
    Alain BIEM; Shigeru KATAGIRI; Biing-Hwang JUANG
    IEEE, Neural Networks for Signal Processing III, 392 - 401, Sep. 1993, International conference proceedings
  • A New Learning Algorithm for Minimizing Spotting Errors
    Takashi KOMORI; Shigeru KATAGIRI
    IEEE, Neural Networks for Signal Processing III, 333 - 342, Sep. 1993, International conference proceedings
  • PROTOTYPE-BASED MCE/GPD TRAINING FOR WORD SPOTTING AND CONNECTED WORD RECOGNITION
    E MCDERMOTT; S KATAGIRI
    ICASSP-93 : 1993 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5, I E E E, 2 B291 - B294, 1993, International conference proceedings
  • FEATURE-EXTRACTION BASED ON MINIMUM CLASSIFICATION ERROR GENERALIZED PROBABILISTIC DESCENT METHOD
    A BIEM; S KATAGIRI
    ICASSP-93 : 1993 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5, I E E E, 2 B275 - B278, 1993, International conference proceedings
  • AN OPTIMAL LEARNING-METHOD FOR MINIMIZING SPOTTING ERRORS
    T KOMORI; S KATAGIRI
    ICASSP-93 : 1993 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5, I E E E, 2 B271 - B274, 1993, International conference proceedings
  • Re-evaluation of lvq-hmm hybrid algorithm
    Hitoshi Iwamida; Shigeru Katagiri; Erik McDermott
    Journal of the Acoustical Society of Japan (E) (English translation of Nippon Onkyo Gakkaishi), 14(4) 267 - 274, 1993, Scientific journal
  • A minimum-distortion segmentation/LVQ hybrid algorithm for speech recognition
    Andrew Duchon; Shigeru Katagiri
    Journal of the Acoustical Society of Japan (E), 14(1) 37 - 42, 1993, Scientific journal
  • DISCRIMINATIVE LEARNING FOR MINIMUM ERROR CLASSIFICATION
    BH JUANG; S KATAGIRI
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 40(12) 3043 - 3054, Dec. 1992, Scientific journal
  • APPLICATION OF A GENERALIZED PROBABILISTIC DESCENT METHOD TO DYNAMIC TIME WARPING-BASED SPEECH RECOGNITION
    T KOMORI; S KATAGIRI
    ICASSP-92 - 1992 INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5, I E E E, 1 A497 - A500, 1992, International conference proceedings
  • PROTOTYPE-BASED DISCRIMINATIVE TRAINING FOR VARIOUS SPEECH UNITS
    E MCDERMOTT; S KATAGIRI
    ICASSP-92 - 1992 INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5, I E E E, 1 A417 - A420, 1992, International conference proceedings
  • GPD training of dynamic programming-based speech recognizers
    Takashi Komori; Shigeru Katagiri
    Journal of the Acoustical Society of Japan (E), 13(6) 341 - 349, 1992, Scientific journal
  • Discriminative training
    Biing-Hwang Juang; Shigeru Katagiri
    Journal of the Acoustical Society of Japan (E), 13(6) 333 - 339, 1992, Scientific journal
  • New Discriminative Training Algorithms Based on the Generalized Probabilistic Descent Method
    Shigeru KATAGIRI; Chin-Hui LEE; Biing-Hwang JUANG
    IEEE, Neural Networks for Signal Processing, 299 - 308, Sep. 1991, International conference proceedings
  • Discriminative Multi-Layer Feed-Forward Networks
    Shigeru KATAGIRI; Chin-Hui LEE; Biing-Hwang JUANG
    IEEE, Neural Networks for Signal Processing, 11 - 20, Sep. 1991, International conference proceedings
  • LVQ-BASED SHIFT-TOLERANT PHONEME RECOGNITION
    E MCDERMOTT; S KATAGIRI
    IEEE TRANSACTIONS ON SIGNAL PROCESSING, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 39(6) 1398 - 1411, Jun. 1991, Scientific journal
  • A MINIMUM ERROR APPROACH TO SPEECH AND PATTERN-RECOGNITION
    BH JUANG; S KATAGIRI
    CONFERENCE RECORD OF THE TWENTY-FIFTH ASILOMAR CONFERENCE ON SIGNALS, SYSTEMS & COMPUTERS, VOLS 1 AND 2, I E E E, COMPUTER SOC PRESS, 959 - 963, 1991, International conference proceedings
  • SPEAKER-INDEPENDENT LARGE VOCABULARY WORD RECOGNITION USING AN LVQ HMM HYBRID ALGORITHM
    H IWAMIDA; S KATAGIRI; E MCDERMOTT
    ICASSP 91, VOLS 1-5, I E E E, S8 553 - 556, 1991, International conference proceedings
  • A NEW CONNECTED WORD RECOGNITION ALGORITHM BASED ON HMM LVQ SEGMENTATION AND LVQ CLASSIFICATION
    P RAMESH; S KATAGIRI; CH LEE
    ICASSP 91, VOLS 1-5, I E E E, S2 113 - 116, 1991, International conference proceedings
  • 聴覚・音声知覚モデルと音声情報処理への応用
    片桐 滋
    人工知能学会誌, 6(3) 351 - 357, 1991
  • On the Robustness of HMM and ANN Speech Recognition Algorithms
    Yasuhiro MINAMI; Toshiyuki HANAZAWA; Hitoshi IWAMIDA; Erik MCDERMOTT; Kiyohiro SHIKANO; Shigeru KATAGIRI; Masao NAKAGAWA
    Proc. ICSLP90, 1345 - 1348, Nov. 1990, International conference proceedings
  • A Large-Scale Japanese Speech Database
    Yoshinori SAGISAKA; Masanobu ABE; Tetsuo UMEDA; Shigeru KATAGIRI; Kazuya TAKEDA; Hisao KUWABARA
    Proc. ICSLP90, 1089 - 1092, Nov. 1990, International conference proceedings
  • A NEW HMM/LVQ HYBRID ALGORITHM FOR SPEECH RECOGNITION
    S KATAGIRI; CH LEE
    GLOBECOM 90 - IEEE GLOBAL TELECOMMUNICATIONS CONFERENCE & EXHIBITION, VOLS 1-3, I E E E, 1032 - 1036, 1990, International conference proceedings
  • A hybrid speech recognition system using HMMs with an LVQ-trained codebook
    Hitoshi Iwamida; Shigeru Katagiri; Erik Mcdermott; Yoh’ichi Tohkura
    Journal of the Acoustical Society of Japan (E), 11(5) 277 - 286, 1990, Scientific journal
  • ATR Japanese speech database as a tool of speech recognition and synthesis
    Akira Kurematsu; Kazuya Takeda; Yoshinori Sagisaka; Shigeru Katagiri; Hisao Kuwabara; Kiyohiro Shikano
    Speech Communication, 9(4) 357 - 363, 1990, Scientific journal
  • A HYBRID SPEECH RECOGNITION SYSTEM USING HMMS WITH AN LVQ-TRAINED CODEBOOK
    H IWAMIDA; S KATAGIRI; E MCDERMOTT; Y TOHKURA
    ICASSP 90, VOLS 1-5, I E E E, 489 - 492, 1990, International conference proceedings
  • Construction of a Large-Scale Japanese Speech Database and its Management System
    H. KUWABARA; K. TAKEDA; Y. SAGISAKA; S. KATAGIRI; S. MORIKAWA; T. WATANABE
    IEEE, Proc. ICASSP89, S10 560 - 563, May 1989, International conference proceedings
  • A New Algorithm for Representing Acoustic Feature Dynamics
    Shigeru KATAGIRI; Erik MCDERMOTT; Manami YOKOTA
    IEEE, Proc. ICASSP89, S6 322 - 325, May 1989, International conference proceedings
  • Shift-Invariant, Multi-Category Phoneme Recognition Using Kohonen's LVQ2
    Erik MCDERMOTT; Shigeru KATAGIRI
    IEEE, Proc. ICASSP89, S3 81 - 84, May 1989, International conference proceedings
  • Development of Japanese Speech Database for Study
    Kazuya TAKEDA; Yoshinori SAGISAKA; Shigeru KATAGIRI; Hisao KUWABARA
    J. Acoust. Soc. Jpn., 44(10) 747 - 754, Oct. 1988, Scientific journal
  • Phoneme Recognition Using Visual Features on Speech Spectrograms
    Shigeru KATAGIRI; Manami YOKOTA
    Proc. European Conf. on Speech Tech., 1 365 - 368, Sep. 1987, International conference proceedings
  • Acoustic-Phonetic Labels in a Japanese Speech Database
    Kazuya TAKEDA; Yoshinori SAGISAKA; Shigeru KATAGIRI
    Proc. European Conf. on Speech Tech., 2 13 - 16, Sep. 1987, International conference proceedings
  • Role of Temporal Information in Phoneme Perception
    Shigeru KATAGIRI; Yoh'ichi TOHKURA
    J. Acoust. Soc. Jpn., 42(2) 97 - 105, Feb. 1986, Scientific journal
  • A new method of cepstrum analysis using comb type quefrency window
    Ghen Ohyama; Sigeru Katagiri; Ken’ichi Kido
    Journal of the Acoustical Society of Japan (E) (English translation of Nippon Onkyo Gakkaishi), 2(3) 135 - 139, 1981, Scientific journal
  • A New Method of Cepstrum Analysis by Using Comb Filter
    Gen OOYAMA; Shigeru KATAGIRI; Ken'ichi KIDO
    3 19 - 22, Apr. 1978, International conference proceedings

MISC

  • Introduction to Deep Learning Toolkit for Speech and Language Processing
    Tsubasa Ochiai; Tatsuya Mitsuhiro; Shigeki Matsuda; Shigeru Katagiri
    Proc. ASJ, 日本音響学会, 73(1) 63 - 72, Jan. 2017, Introduction scientific journal
  • 高臨場感を与える視聴覚ディスプレイのための音像制御システム
    中谷 彰皓; 片桐 滋; 大崎 美穂
    情報処理学会研究報告. GN, [グループウェアとネットワークサービス], 一般社団法人情報処理学会, 2015(23) 1 - 6, 05 Mar. 2015
  • ローカル・ラグ制御を伴うマルチメディア伝送サーバの構築
    李 榮宰; 片桐 滋; 大崎 美穂
    情報処理学会研究報告. GN, [グループウェアとネットワークサービス], 一般社団法人情報処理学会, 2015(22) 1 - 8, 05 Mar. 2015
  • Relation between Data Grouping and Robustness to Unseen Data in Large Geometric Margin Minimum Classification Error Training
    SHIRAISHI Hiroyuki; WATANABE Hideyuki; KATAGIRI Shigeru; Lu XUGANG; HORI Chiori; OHSAKI Miho
    Technical report of IEICE. Multimedia and virtual environment, The Institute of Electronics, Information and Communication Engineers, 114(410) 177 - 182, 22 Jan. 2015
  • Analysis of Minimum Classification Error Training using Bit-String-Based Genetic Algorithms
    TOGOE Hiroto; WATANABE Hideyuki; KATAGIRI Shigeru; LU Xugang; HORI Chiori; OHSAKI Miho
    Technical report of IEICE. Multimedia and virtual environment, The Institute of Electronics, Information and Communication Engineers, 114(410) 171 - 176, 22 Jan. 2015
  • Analysis of Minimum Classification Error Training using Bit-String-Based Genetic Algorithms
    外越 寛人; 渡辺 秀行; 片桐 滋; ル シュガン; 堀 智織; 大崎 美穂
    IPSJ SIG Notes. CVIM, Information Processing Society of Japan (IPSJ), 2015(30) 1 - 6, 15 Jan. 2015
  • Relation between Data Grouping and Robustness to Unseen Data in Large Geometric Margin Minimum Classification Error Training
    白石 裕之; 渡辺 秀行; 片桐 滋; ル シュガン; 堀 智織; 大崎 美穂
    IPSJ SIG Notes. CVIM, Information Processing Society of Japan (IPSJ), 2015(31) 1 - 6, 15 Jan. 2015
  • Moving Image Object Extraction with Infrared Sensor for "t-Room"
    上埜敏司; 片桐滋; 大崎美穂
    2014年度 情報処理学会関西支部 支部大会 講演論文集, [情報処理学会関西支部], 2014 7p , 10 Sep. 2014
  • Experimental Evaluation of Automatic Optimization Methods for the Number of Prototypes in Minimum Classification Error Training
    荻野将大; 渡辺秀行; 片桐滋; 大崎美穂; 堀智織
    2014年度 情報処理学会関西支部 支部大会 講演論文集, [情報処理学会関西支部], 2014 8p , 10 Sep. 2014
  • Experimental Evaluation of Acoustic Server Having Local-lag Control
    大島義博; 片桐滋; 大崎美穂
    2014年度 情報処理学会関西支部 支部大会 講演論文集, [情報処理学会関西支部], 2014 8p , 10 Sep. 2014
  • A New Speaker Setup for Avoiding Visual Occlusion in Sound Image Production Method using Flat Display and Acoustic Barriers
    山下春香; 片桐滋; 大崎美穂
    2014年度 情報処理学会関西支部 支部大会 講演論文集, [情報処理学会関西支部], 2014 6p , 10 Sep. 2014
  • On Data Partitioning for Large-Geometric-Margin-Based Training
    白石裕之; 竹中一馬; 渡辺秀行; 片桐滋; 大崎美穂; 堀智織
    2014年度 情報処理学会関西支部 支部大会 講演論文集, [情報処理学会関西支部], 2014 8p , 10 Sep. 2014
  • Guest Editorial: Machine Learning for Signal Processing
    Shigeru Katagiri; Atsushi Nakamura; Tuelay Adali; Jianhua Tao; Jan Larsen; Tieniu Tan
    JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, SPRINGER, 74(3) 281 - 283, Mar. 2014, Others
  • 身体動作を伴うコラボレーションのためのメディア空間
    電子情報通信学会 総合大会, 2014, Summary national conference
  • 話者正規化学習されたディープニューラルネットワークによる教師なし話者適応
    日本音響学会春季研究発表会, 2014
  • プロトタイプ数の自動的最適化を伴う大幾何マージン最小分類誤り学習法
    電子情報通信学会 パターン認識とメディア理解 研究会, 2014
  • 最小分類誤り基準に基づく多クラスサポートベクターマシン
    電子情報通信学会 パターン認識とメディア理解 研究会, 2014
  • カーネル写像を用いた最小分類誤り学習法
    電子情報通信学会 パターン認識とメディア理解 研究会, 2014
  • クラス共通損失関数平滑度の自動設定法を伴う最小分類誤り学習法
    電子情報通信学会 パターン認識とメディア理解 研究会, 2014
  • Linux版t-Roomの開発:デバイス制御システムの設計と実装
    情報処理学会 グループウェアとネットワークサービス 研究会, 2014
  • ローカル・ラグ制御機能を持つ音楽同期演奏システムの提案
    情報処理学会 グループウェアとネットワークサービス 研究会, 2014
  • ディープラーニング事前学習の効果に関するユニット出力可視化を通した実験的考察
    電子情報通信学会 パターン認識とメディア理解 研究会, 2014
  • Proposal of the Dynamic Features of Clinical Time Series for the Prediction of Liver Fibrosis Stages in Chronic Hepatitis C
    Shigeru KATAGIRI
    Japan Journal of Medical Informatics, 33(2) 79 - 98, 2013
  • C型慢性肝炎の肝線維化ステージ推定を目指した検査値時系列区分化の影響の検証
    情報処理学会 バイオ情報学研究会, 2013
  • C型慢性肝炎の肝線維化ステージ推定を目指したスペクトラム推定量に基づく特徴量の比較
    情報処理学会 バイオ情報学研究会, 2013
  • 映像の有無を伴う音響反射板方式の音像定位精度の評価
    電子情報通信学会 応用音響研究会, 2013
  • 遠隔コラボレーション支援システム「t-Room」のための顔認識技術の検討
    電子情報通信学会総合全国大会, 2013, Summary national conference
  • 遠隔コラボレーション支援システム"t-Room"における重ね合わせ映像表示法に関する検討
    電子情報通信学会総合全国大会, 2013, Summary national conference
  • 遠隔コラボレーション支援システム「t-Room」のためのSIPを用いた接続手法の提案
    電子情報通信学会総合全国大会, 2013, Summary national conference
  • 音響反射板方式を用いた映像と音像の同時提示における聞こえの質の評価
    日本音響学会春季研究発表会, 2013
  • 音響反射板方式における映像と音像定位の相互作用に関する評価
    日本音響学会春季研究発表会, 2013
  • 遠隔コラボレーション支援のための映像伝送システムの開発とその遅延評価
    情報処理学会 グループウェアとネットワークサービス 研究会, 2013
  • 自然な獲得動作に倣うデータ転送法の提案
    ヒューマンインタフェース学会研究会, 2012
  • ローカル・ラグ制御機能と同期機能を持つ音響サーバの性能評価
    情報処理学会関西支部大会, 2012
  • 音響反射板方式における複数音像生成の性能評価
    日本音響学会秋季研究発表会, 2012
  • 大幾何マージン最小分類誤り学習法における仮想標本生成の効果の検証
    画像の認識・理解シンポジウム(MIRU2012), 2012, Summary national conference
  • C型慢性肝炎の肝線維化ステージ予測に適する特徴量の検討
    第39回知能システムシンポジウム, 2012
  • スマートフォンを利用した遠隔コラボレーション支援システム「t-Room」の拡張
    電子情報通信学会総合大会, 2012, Summary national conference
  • t-RoomにおけるSIPを用いた動的なVPN接続環境の構築
    電子情報通信学会総合大会, 2012, Summary national conference
  • 位置情報に基づくインタラクティブ映像探索手法の提案
    映像情報メディア学会 ヒューマンインフォメーション研究会, 2012
  • C型慢性肝炎の肝線維化ステージ予測に役立つ特徴量の提案
    第32回東海ファジィ研究会, 2012
  • C型慢性肝炎の肝線維化ステージ分類手法の比較
    第32回東海ファジィ研究会, 2012
  • 遠隔協働支援システム「t-Room」における映像オブジェクト抽出法の改良
    電子情報通信学会 画像工学研究会, 2012
  • 遠隔コラボレーション支援システム「t-Room」における複数カメラ映像を用いた利用者追跡
    電子情報通信学会 画像工学研究会, 2012
  • 粒子フィルタと最小分類誤り学習を用いた映像オブジェクト追跡法の検討
    電子情報通信学会 画像工学研究会, 2012
  • 単眼カメラを搭載したラジコンヘリコプターを用いた全周パノラマ画像の生成
    電子情報通信学会 画像工学研究会, 2012
  • ローカル・ラグ制御機能を持つ音響サーバを用いた遠隔合奏の評価
    情報処理学会 オーディオビジュアル複合商法処理 研究会, 2012
  • ローカル・ラグ制御機能とログ同期機能を持つ音響サーバの開発
    情報処理学会 オーディオビジュアル複合情報処理 研究会, 2012
  • Minimum Classification Error Training using Geometric-Margin-Based Misclassification Measure
    Shigeru KATAGIRI
    IEICE Transactions D, J94D(10) 1664 - 1675, 2011
  • Incremental Minimum Classification Error Training for Pattern Recognition
    Shigeru KATAGIRI
    IEICE Transactions D, J94D(4) 702 - 711, 2011
  • 平面ディスプレイと音響反射板を用いた音像生成システムの受聴実験評価
    日本音響学会秋季研究発表会, 2011
  • 大幾何マージン最小分類誤り学習に対する損失関数平滑度の自動制御の適用
    電子情報通信学会 パターン認識とメディア理解 研究会, 2011
  • 多チャンネル音響インタフェースを用いた平面ディスプレイ上の音像生成システムの構築
    日本音響学会 第13回関西支部若手研究者交流研究発表会, 2010, Summary national conference
  • カーネルに基づく高次元空間における大幾何マージン最小分類誤り学習の提案
    電子情報通信学会 パターン認識とメディア理解 研究会, 2010
  • プロトタイプ型分類器設計における最小分類誤り学習法とサポートベクターマシンの比較
    電子情報通信学会 パターン認識とメディア理解 研究会, 2010
  • t-Roomにおける接続先実行環境を考慮した動的制御の提案と開発
    情報処理学会 マルチメディア通信と分散処理 研究会, 2010
  • t-Room環境に適したVPN接続手法の選定とQoSによる動的通信帯域制御手法の提案
    情報処理学会 マルチメディア通信と分散処理 研究会, 2010
  • LinuxルータとSIPサーバを用いたt-Room間接続環境の構築
    情報処理学会関西支部大会, 2010
  • 遠隔コミュニケーション環境の評価を目指した話者遷移のモデル化
    情報処理学会関西支部大会, 2010
  • ローカルラグ制御機能を持つ音響システムの改良
    情報処理学会関西支部大会, 2010
  • 遠隔協働支援システムt-Roomにおける映像エコー・キャンセリング法の実装と実験的評価
    情報処理学会関西支部大会, 2010
  • 損失関数平滑度の自動制御を伴う最小分類誤り学習法
    電子情報通信学会 パターン認識とメディア理解 研究会, 2010
  • 自己回帰モデルに基づく時系列医療データの予後分類
    第24回人工知能学会全国大会, 2010
  • タスク依存性に着目した遠隔コミュニケーション環境の比較評価
    インタラクション2010, 2010, Summary national conference
  • Towards Maximum Geometric Margin Minimum Error Classification
    Shigeru KATAGIRI
    The Science and Engineering Review of Doshisha University, 50(3) 43 - 52, 2009
  • 映像フィードバックに伴うエコーのキャンセリング法に関する実験的評価
    電子情報通信学会 パターン認識とメディア理解 研究会, 2009
  • 粒子フィルタと最小分類誤り学習を用いる指映像認識
    電子情報通信学会 パターン認識とメディア理解 研究会, 2009
  • t-Roomのための遠隔合奏支援システムの構築
    情報処理学会 グループウェアとネットワークサービス研究会, 2009
  • 未来の電話「t-Room」のための開発支援システムの提案
    情報処理学会 システム評価研究会, 2009
  • 大幾何マージン最小分類誤り学習法
    情報論的学習理論ワークショップ2009, 2009
  • アンサンブル型最小分類誤り学習法の実装と実験的評価
    電子情報通信学会 パターン認識とメディア理解 研究会, 2009
  • 判別関数の一般形に対する幾何マージンの導出とその制御を伴う最小分類誤り学習
    電子情報通信学会 パターン認識とメディア理解 研究会, 2009
  • 最小分類誤り学習における幾何マージンの制御法について
    電子情報通信学会 音声研究会, 2009
  • 収音方法がスピーカ受聴における音像定位に与える影響の分析
    2009年日本音響学会春季研究発表会, 2009
  • アンサンブル型最小分類誤り学習の提案
    電子情報通信学会 パターン認識とメディア理解 研究会, 2009
  • 遠隔協働における参加者位置関係情報の影響の分析
    インタラクション2009, 2009, Summary national conference
  • 未来の電話「t-Room」の機能強化に向けて
    インタラクション2009, 2009, Summary national conference
  • 回帰診断に基づく医療データの補間の検討
    第7回情報科学技術フォーラム, 2008
  • 移動平均法に基づく部分時系列クラスタリングの再解釈
    第22回人工知能学会全国大会, 2008
  • 遠隔共創空間のための発話者位置同定法に関する基礎検討
    第10回日本音響学会開催支部若手研究者発表会, 2007, Summary national conference
  • Advanced computational models and learning theories for spoken language processing
    Atsushi Nakamura; Shinji Watanabe; Takaaki Hori; Erik McDermott; Shigeru Katagiri
    IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC, 1(2) 5 - +, May 2006, Introduction scientific journal
  • A Study of Word and Sentence Acquisition: Quantitative Analysis of Longitudial Data
    Shigeru KATAGIRI
    Cognitive Studies, 10(2) 304 - 317, 2003
  • 言語獲得過程の定量的分析 (III) 発達関数の数理的考察
    乾敏郎; 大庭真人; 天野成昭; 片桐滋
    日本心理学会大会発表論文集, 66th 802 , Aug. 2002
  • A Recogniton Method with Parametric Trajectory Synthesized Using Direct Relations Between Static and Dynamic Feature Vector Time Series
    MINAMI Yasuhiro; MCDERMOTT Erik; NAKAMURA Atsushi; KATAGIRI Shigeru
    日本音響学会研究発表会講演論文集, 2002(1) 83 - 84, 18 Mar. 2002
  • LANGUAGE MODEL SYNCHRONIZATION FOR IMPROVED BEAM-SEARCH PERFORMANCE IN LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION
    WILLETT Daniel; MCDERMOTT Erik; MINAMI Yasuhiro; KATAGIRI Shigeru
    日本音響学会研究発表会講演論文集, 2001(2) 99 - 100, 01 Oct. 2001
  • 言語獲得過程の定量的分析 (II) 言語使用の母子間の相関
    乾敏郎; 天野成昭; 近藤公久; 片桐滋
    日本心理学会大会発表論文集, 65th 485 , Oct. 2001
  • 「知」のモデルを求めて‐知能情報研究の過去,現在, 未来‐
    片桐 滋
    NTT R&D, 50(5) 336 - 346, May 2001, Introduction research institution
  • A TIME-SYNCHRONOUS VITERBI-DECODER FOR ARBITRARY SPEECH RECOGNITION TASKS DEFINED BY FINITE STATE TRANSDUCERS
    WILLETT Daniel; MCDERMOTT Erik; MINAMI Yasuhiro; NAKAMURA Atsushi; KATAGIRI Shigeru
    日本音響学会研究発表会講演論文集, 2001(1) 13 - 14, 01 Mar. 2001
  • Towards a Model of Intelligence Systems: The Past, Present, and Future of Intelligent Communication Systems
    Shigeru KATAGIRI
    NTT R&D, 50(5) 336 - 346, 2001
  • 言語獲得過程の定量的分析
    乾敏郎; 小林章子; 天野成昭; 近藤公久; 片桐滋
    日本心理学会大会発表論文集, 64th 776 , 2000
  • Speaker Recognition Based on Discriminative Feature Extraction : Optimization of Mel-Cepstral Features
    MIYAJIMA Chiyomi; WATANABE Hideyuki; TOKUDA Keiichi; KITAMURA Tadashi; KATAGIRI Shigeru
    IEICE technical report. Speech, The Institute of Electronics, Information and Communication Engineers, 99(256) 1 - 8, 06 Aug. 1999
  • Development of the generalized probabilistic descent method
    Shigeru KATAGIRI
    J. Acoust. Soc. Jpn., The Acoustical Society of Japan (ASJ), 55(8) 563 - 568, Aug. 1999, Introduction scientific journal
  • Speaker Recognition Based on Discriminative Feature Extraction -Optimization of Mel-Cepstral Features Based on Second-Order All-Pass Function
    MIYAJIMA Chiyomi; WATANABE Hideyuki; TOKUDA Keiichi; KITAMURA Tadashi; KATAGIRI Shigeru
    日本音響学会研究発表会講演論文集, 1999(1) 35 - 36, 01 Mar. 1999
  • インターネットでL/Rに挑戦しませんか?‐基礎研究成果をマルチメディア発信‐
    片桐 滋
    NTT技術ジャーナル, 145 - 147, Oct. 1998, Introduction research institution
  • Let's study L/R hearing with the Internet: Multimedia publicity of research outputs
    Shigeru KATAGIRI
    NTT Technical Journal, 145 - 147, 1998
  • OPTIMIZING CONTINUOUS PHONEME RECOGNITION USING MCE
    MCDERMOTT Erik; KATAGIRI Shigeru
    日本音響学会研究発表会講演論文集, 1997(1) 193 - 194, 01 Mar. 1997
  • Auditory/Speech-perception Modeling and Its Applications to Speech Processing
    Shigeru KATAGIRI
    J. Japanese Society for Artificial Intelligence, 6(3) 351 - 357, 1991
  • A Japanese speech database for various kinds of research purposes
    Shigeru KATAGIRI
    J. Acoust. Soc. Jpn., The Acoustical Society of Japan (ASJ), 44(10) 747 - 754, 1988
  • A role of duration in syllable perception
    S. KATAGIRI
    J. Acoust. Soc. Jpn., 42(2) 97 - 105, 1986
  • スペクトルリーディングに基づく音韻特徴探索システム
    片桐 滋; 古井 貞熙
    日本音響学会 音声研究会資料 S84-56, 437 - 444, 1984

Books etc

  • Pattern Recognition in Speech and Language Processing
    Shigeru KATAGIRI
    CRC Press, Feb. 2003, Contributor, Chapter 4 "Speech Pattern Recognition Using Neural Networks"
  • Handbook of Neural Network Signal Processing
    Shigeru KATAGIRI
    CRC Press, Aug. 2001, Contributor, Chapter 10 "Applications of Artificial Neural Networks to Speech Processing"
  • Nonlinear Dynamical Systems -Feedforward Neural Network Perspective-
    Irwin W; SANDBERG; James T. LO; Craig L. FANCOURT; Jose C. PRINCIPE; Shigeru KATAGIRI; Simon HAYKIN
    John Wiley & Sons, Feb. 2001, Joint work, Chapter 5 "Application of Feedforward Networks to Speech"
  • Intelligent Signal Processing
    Shigeru KATAGIRI; Biing-Hwang JUANG; Chin-Hui LEE
    IEEE Press, Jan. 2001, Contributor, Pattern Recognition Using a Family of Design Algorithms Based Upon the Generalized Probabilistic Descent Method
  • Handbook of Neural Networks for Speech Processing
    Handbook of; Neural Networks for; Speech Processing
    Artech House, Oct. 2000, Joint editor
  • Handbook of Pattern Recognition and Computer Vision
    Shigeru KATAGIRI; Erik MCDERMOTT
    World Scientific Pub., Mar. 1999, Contributor, Discriminative Training -Recent Progress in Speech Recognition
  • Signal Processing Technology and Applications
    Alain BIEM; Shigeru KATAGIRI; Biing-Hwang JUANG
    IEEE Press, Sep. 1995, Contributor, Discriminative Feature Extraction for Speech Recognition
  • Application of Neural Networks
    Shigeru KATAGIRI; Masahide SUGIYAMA
    Ohm, Jul. 1995, Contributor, Chapter 4 "Application to Speech Processing"
  • Applications of Neural Networks
    Ohm Pub., 1995
  • Artificial Neural Networks for Speech and Vision
    Shigeru KATAGIRI; Biing-Hwang JUANG; Alain BIEM
    Chapman & Hall, Jan. 1994, Contributor, Chapter 18 "Discriminative Feature Extraction"
  • Readings in Speech Recognition
    Erik MCDERMOTT; Hitoshi IWAMIDA; Shigeru KATAGIRI; Yoh'ichi TOHKURA
    Morgan Kaufmann, May 1990, Contributor, Shift-Tolerant LVQ and Hybrid LVQ-HMM for Phoneme Recognition

Presentations

  • To Ride the Tide or To Stick with The Basics?
    Shigeru KATAGIRI
    ACM, International Conference on Signal Processing and Machine Learning (SPML2019), Nov. 2019, Keynote oral presentation
  • From Bayes Error to Bayes Boundary
    Shigeru KATAGIRI
    ACM SPML 2018, Nov. 2018, Keynote oral presentation
  • パターン認識課題にどう向き合うか–一般化確率的降下法と最小分類誤り学習法の狭間で-
    片桐 滋
    電子情報通信学会 パターン認識•メディア理解研究会, Dec. 2009, Invited oral presentation, 栃木(鬼怒川)
  • 最新インタラクション技術‐同室感通信t-Roomと要素技術研究の共創を目指す‐
    片桐 滋
    情報通信ネットワーク協会「Adaptive & Scalableデザイン」ワーキングループ, Mar. 2009, Invited oral presentation, 京田辺
  • A New Perspective of Discriminative Training for Pattern Recognition
    Shigeru KATAGIRI
    IEEE and IET, 2008 International Conference on Audio, Language and Image Processing (ICALIP2018), Jul. 2008, Keynote oral presentation, Shanhai
  • パターン認識の原点に立ち返って
    片桐 滋
    IEEE関西セクション・情報通信技術研究交流会共催講演会, Mar. 2008, Invited oral presentation, 大阪

Works

  • t-Roomによる遠隔コラボレーション技術
    2006 -2008
  • Collaboration technology enhanced with t-Room
    2006 -2008

Research Projects

  • Development of Class Boundary Evaluation Criterion in Pattern Recognition
    Shigeru KATAGIRI
    JSPS, KAKENHI (B), 2018/04 -2022/03, Principal investigator, Competitive research funding
  • MCE-Criterion-Based Approach to Design and Search of Discriminative Feature Space
    Shigeru Katagiri
    JSPS, KAKENHI (B), 2014/04 -2017/03, Principal investigator, Competitive research funding
  • Study on Achievable Performances of Minimum Classification Error Training
    Shigeru Katagiri
    JSPS, KAKENHI (B), 2010/04 -2012/03, Principal investigator, Competitive research funding
  • Systematization and Generalization of Discriminative Training
    Shigeru Katagiri
    JSPS, KAKENHI (B), 2007/04 -2009/03, Principal investigator, Competitive research funding

Social Contribution

  • 東北大学大学院工学研究科電気・情報系グローバルCOE第三者評価委員会 委員, 2008-2012, Research advise
  • 東北大学電気通信研究所運営協議会 委員, 2006-2007, Research advise
  • サイバー創研 技術顧問, 2006, Research advise
  • Member, Industrial Advisory Board, Dept. EE, University of Washington, 2006, Research advise

Research Seeds

  • Discriminative training methods for pattern recognition
    Research Fields: Information and Communication
    Affiliation/Name: Shigeru Katagiri