LEE Akinobu

写真a

Affiliation Department etc.

Department of Computer Science
Department of Computer Science

Title

Professor

Mail Address

E-mail address

Homepage URL

http://www.slp.nitech.ac.jp/

Research Fields, Keywords

Spoken Language Processing, Speech Recognition, Spoken Dialog System, Speech Interaction

Graduating School

  •  
    -
    1996.03

    Kyoto University   Faculty of Engineering   Department of Information Science   Graduated

Graduate School

  •  
    -
    2000.09

    Kyoto University  Graduate School, Division of Information and Communication  Department Intelligence Science and TechnologyDoctor's Course  Completed

  •  
    -
    1998.03

    Kyoto University  Graduate School, Division of Engineering  Department of Information ScienceMaster's Course  Completed

Degree

  • Kyoto University -  Ph.D. on Informatics

External Career

  • 2005.04
    -
    2016.03

      Associate Professor  

  • 2000.10
    -
    2005.03

      Research Assistant  

Field of expertise (Grants-in-aid for Scientific Research classification)

  • Intelligent informatics

  • Perceptual information processing

  • Multimedia database

 

Research Career

  • Speech Recognition, Spoken Language Processing and Understanding, Spoken Dialog System,. Search Algorithm

    International Collaboration   (not selected)  

    Project Year:  2000.10  -  Now

    General topics of speech recognition, spoken language understanding and dialog system

Thesis for a degree

  • Large Vocabulary Continuous Speech Recognition using Multi-Pass Search Algorithm

    Akinobu Lee 

      2000.09  [Refereed]

    8   1

Papers

  • Prosodically-Enhanced Recurrent Neural Network Language Models

    Siva Reddy Gangireddy, Steve Renals, Yoshihiko Nankaku, Akinobu Lee

    Proc. Conference of the International Speech Communiation Association (INTERSPEECH)     2390 - 2394   2015.09  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • Voice interaction system with 3D-CG virtual agent for stand-alone smartphones

    Daisuke Yamamoto, Keiichiro Oura, Ryota Nishimura, Takahiro Uchirya, Akinobu Lee, Ichi Takumi, Keiichi Tokuda

    the 2nd International Conference on Human Agent Interaction (HAI 2014), ACM digital library,     320 - 330   2014.10  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • MMDAgent --- A Fully Open-Source Toolkit for Voice Interaction Systems

    Akinobu Lee, Keiichiro Oura, Keiichi Tokuda.

    IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2013     8382 - 8385   2013.05  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • Speech recognition based on statistical models including multiple phonetic decision trees

    Sayaka Shiota, Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

    Acoustical Science and Technology   32 ( 6 ) 236 - 243   2011.11  [Refereed]

    Research paper (scientific journal)   Multiple Authorship

  • Evaluation of Tree-Trellis Based Decoding on Over-Million LVCSR

    Naoaki Ito, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

    Proc. ISCA Interspeech2011     1937 - 1940   2011.08  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • Bayesian context clustering using cross validation for speech recognition(共著)

    Kei Hashimoto, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

    IEICE Transactions on Information and Systems   E94-D ( 3 ) 668 - 678   2011.03  [Refereed]

    Research paper (scientific journal)   Multiple Authorship

  • Speaker Adaptation Based on Nonlinear Spectral Transform for Speech Recognition(共著)

    Toyohiro Hayashi, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

    Proc. Conference of the International Speech Communiation Association (INTERSPEECH)     542 - 545   2010.09  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • Voice activity detection based on conditional random fields using multiple features(共著)

    Akira Saito, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

    Proc. Conference of the International Speech Communiation Association (INTERSPEECH)     2086 - 2089   2010.09  [Refereed]

    Research paper (international conference proceedings)   Multiple Authorship

  • A Covariance-Tying Technique for HMM-Based Speech Synthesis(共著)

    Keiichiro Oura, Heiga Zen, Yoshihiko Nankaku, Akinobu Lee, Keiichi Tokuda

    IEICE Transactions on Information and Systems   93 ( 3 ) 595 - 601   2010.03  [Refereed]

    Research paper (scientific journal)   Multiple Authorship

  • 音声認識のデコーダと認識エンジン

    李晃伸

    日本音響学会誌 日本音響学会   66 ( 1 ) 28 - 31   2010.01  [Refereed]

    Research paper (scientific journal)   Single Author

display all >>

Books

  • Chapter 7.2-2 Common platform of Japanese LVCSR assessment in "Resources and Standards of Spoken Language Systems - Advances in Oriental Spoken Language Processing"

    (Part: Multiple Authorship )

    World Scientific Publishing Co.  2010.04

Review Papers

  • On-Campus, User-Participatable, and Voice-Interactive Digital Signage

    Keiichiro Oura, Daisuke Yamamoto, Ichi Takumi, Akinobu Lee, Keiichi Tokuda

    Academic Journal of The Japanese Society of Artifical Intelligence ( The Japanese Society of Artifical Intelligence )  28 ( 1 ) 60 - 67   2013.01

    Introduction and explanation (international conference proceedings)   Multiple Authorship

  • Technical Advances of Speech-Oriented Guidance System "Takemaru-kun" by 10 Years of Long-Term Operation

    Ryuichi Nisimura, Nao Hara, Hiromichi Kawanami, Akinobu Lee, Kiyohiro Shikano

    Academic Journal of the Japanese Society for Artificial Intelligence ( The Japanese Society for Artificial Intelligence )  28 ( 1 ) 52 - 59   2013.01

    Introduction and explanation (international conference proceedings)   Multiple Authorship

  • Speech recognition decoder and recognition engine

    LEE Akinobu

    Acoustical Science and Technology ( Acoustical Society of Japan )  66 ( 1 ) 28 - 31   2009.12

    Introduction and explanation (international conference proceedings)   Single Author

  • Development of speech recognition interface using Julius

    Akinobu Lee, Tatsuya Kawahara

    Human Interface ( Human Interface Society )  11 ( 1 ) 31 - 38   2009.02

    Introduction and explanation (international conference proceedings)   Multiple Authorship

  • Large-vocabulary continuous speech recognition engine Julius

    LEE Akinobu

    The transactions of the Institite of Electronics, Information and Communication Engineers ( The Institite of Electronics, Information and Communication Engineers )  13 ( 4 )   2009.02

    Introduction and explanation (international conference proceedings)   Single Author

Presentations

  • Spoken keyword detection using recurrent neural network language model

    Shuhei Koike, Akinobu Lee

    5th Joint Meeting Acoustical Society of America and Acoustical Society of Japan  (Honolulu, Hawaii)  2016.11  -  2016.12  Acoustical Society of America and Acoustical Society of Japan

  • 自然言語理解を用いた車載音声インタフェースの評価に用いるプロトタイピングシステムの開発

    李 晃伸, 神沼 充伸, Christoph Neumann

    自動車技術会2016年秋季大会  (札幌コンベンションセンター)  2016.10  -  2016.10  公益社団法人自動車技術会

  • スマートフォン単体で動作する音声対話3Dエージェント「スマートメイちゃん」の開発

    山本大介, 大浦圭一郎, 西村良太, 打矢隆弘, 内匠逸, 李晃伸, 徳田恵一

    インタラクション2013  (日本科学未来館)  2013.03  -  2013.03  情報処理学会

Work

  • MMDAgent: Toolkit for Building Voice Interaction Systems Ver.1.5

    Software  2014.12  -  2014.12

  • Julius dictation runkit (DNN version) v4.3.1

    Software  2014.01  -  2014.01

  • MMDAgent: Toolkit for Building Voice Interaction Systems Ver.1.4

    Software  2013.12  -  2013.12

  • Large Vocabulary Continous Speech Recognition System Julius ver.4.3, 4.3.1

    Software  2013.12  -  2013.12

  • Large Vocabulary Continous Speech Recognition System Julius ver.4.2.3

    Software  2013.06  -  2013.06

  • MMDAgent: Toolkit for Building Voice Interaction Systems Ver.1.3.1

    Software  2012.12  -  2012.12

  • Large Vocabulary Continous Speech Recognition System Julius ver.4.2.2

    Software  2012.08  -  2012.08

Academic Awards Received

  • IPSJ Yamashita SIG Research Award

    2007.04    

  • ASJ Kiyoshi Awaya Award

    2002.04    

Other external funds procured

  • European Commission

    Offer organization: European Commission  European Commission

    Project Year: 2008  -  2011 

 
 

Academic Activity

  • 2016.04
    -
    Now

    Information Processing Society of Japan  

  • 2015.09
     
     

    Acoustical Society of Japan  

  • 2014.04
    -
    2016.03

    Information Processing Society of Japan  

  • 2011.04
    -
    2014.03

    Information Processing Society of Japan  

  • 2010.04
    -
    2012.03

    Information Processing Society of Japan