• Search Research Projects
  • Search Researchers
  • How to Use
  1. Back to project page

2013 Fiscal Year Final Research Report

Study on spoken language understanding framework integrating knowkedges among multiple layers

Research Project

  • PDF
Project/Area Number 21300066
Research Category

Grant-in-Aid for Scientific Research (B)

Allocation TypeSingle-year Grants
Section一般
Research Field Perception information processing/Intelligent robotics
Research InstitutionNagoya Institute of Technology

Principal Investigator

LEE Akinobu  名古屋工業大学, 工学(系)研究科(研究院), 准教授 (80332766)

Co-Investigator(Kenkyū-buntansha) KOMATANI Kazunori  名古屋大学, 工学(系)研究科(研究院), 准教授 (40362579)
NANJO Hiroaki  龍谷大学, 理工学部, 助教 (50388162)
NISIMURA Ryuuichi  和歌山大学, システム工学部, 助教 (00379611)
NISHIDA Masafumi  同志社大学, 理工学部, 准教授 (80361442)
SHINOZAKI Takahiro  東京工業大学, 総合理工学研究科(研究院), 准教授 (80447903)
AKITA Yuya  京都大学, 学内共同利用施設等, 助教 (90402742)
Project Period (FY) 2009-04-01 – 2014-03-31
Keywords音声認識 / 音声言語理解 / 音声対話 / 音声信号処理
Research Abstract

This study focuses on developing a framework that integrates handling of multiple knowledge layer from speech signal processing to spoken language understanding directly into speech recognition process in a statistical mannar. Statistical models at layers of language model, acoustic model and dialogue model are widely investigated. For integration, speech decoding based on Bayes-risk minimization in which all the constraint can be expressed as Bayes risk, and some integration methods that utilizes speech information for dialogue management and turn taking was investigated. Part of the results are publicly available as part of an open-source voice interaction building tool MMDAgent and Julius.

  • Research Products

    (22 results)

All 2014 2013 2012 2011 2010 2009

All Journal Article (6 results) (of which Peer Reviewed: 6 results) Presentation (16 results) (of which Invited: 5 results)

  • [Journal Article] オープンソース音声認識エンジンJulius へのベイズリスク最小化機能の実装と評価2013

    • Author(s)
      南條浩輝, 古谷遼, 西田昌史
    • Journal Title

      電子情報通信学会論文誌

      Volume: Vol.J96-D, No.10 Pages: 2530-2539

    • Peer Reviewed
  • [Journal Article] 音声入力型情報探索におけるベイズリスク最小化音声認識のための単語重要度の自動推定2013

    • Author(s)
      古谷遼, 七里崇, 南條浩輝
    • Journal Title

      情報処理学会論文誌

      Volume: Vol.54, No.7 Pages: 1967-1977

    • Peer Reviewed
  • [Journal Article] 講演に対する読点の複数アノテーションに基づく自動挿入2013

    • Author(s)
      秋田祐哉
    • Journal Title

      情報処理学会論文

      Volume: Vol.54, No.2 Pages: 463-470

    • Peer Reviewed
  • [Journal Article] 文単位で分割されたテキストで学習した言語モデルによる単語信頼度を用いた文境界検出2011

    • Author(s)
      鈴木伸尚, 西田昌史, 山本誠一
    • Journal Title

      第10回情報科学技術フォーラム(FIT)講演論文集

      Volume: 第2分冊 Pages: 35-38

    • Peer Reviewed
  • [Journal Article] Statistical transformation of language and pronunciation models for spontaneous speech recognition2010

    • Author(s)
      Yuya Akita
    • Journal Title

      IEEE Trans. Audio, Speech & Language Process

      Volume: 18巻 Pages: 1539-1549

    • Peer Reviewed
  • [Journal Article] An Efficient Prosody Application to HMM-based Speech Synthesis2010

    • Author(s)
      Hosan Kamiyama, Takahiro Shinozaki, Koji Iwano and Sadaoki Furui
    • Journal Title

      Proc. Asia‐ Pacific Signal and Information Processing Association (APSIPA)

      Volume: 1巻 Pages: 82-85

    • Peer Reviewed
  • [Presentation] 「音声認識」は今後こうなる!2014

    • Author(s)
      篠崎隆宏
    • Organizer
      SIG-SLP 第100回記念シンポジウム
    • Place of Presentation
      伊豆長岡温泉ホテルサンバレー富士見
    • Year and Date
      20140131-0201
    • Invited
  • [Presentation] Hierarchical Utterance Understanding for Robust Human-Robot Spoken Dialogues2014

    • Author(s)
      Kazunori Komatani
    • Organizer
      International Workshop on Spoken Dialogue Systems (IWSDS2014)
    • Place of Presentation
      Napa, California, US
    • Year and Date
      20140118-20
    • Invited
  • [Presentation] Restoring Incorrectly Segmented Keywords and Turn-Taking Caused by Short Pauses2014

    • Author(s)
      Kazunori Komatani, Naoki Hotta, Satoshi Sato
    • Organizer
      International Workshop on Spoken Dialogue Systems (IWSDS2014)
    • Place of Presentation
      Napa, California, US
    • Year and Date
      20140118-20
  • [Presentation] MMDAgent - A Fully Open-Source Toolkit for Voice Interaction Systems2013

    • Author(s)
      Akinobu Lee, Keiichiro Oura, Keiichi Tokuda
    • Organizer
      IEEE ICASSP2013
    • Place of Presentation
      Vancouver, BC, Canada
    • Year and Date
      20130526-31
  • [Presentation] ユーザ参加型双方向音声案内デジタルサイネージシステムの開発・設置・運用事例2013

    • Author(s)
      徳田 恵一
    • Organizer
      日本音響学会研究発表会
    • Place of Presentation
      東京工科大学
    • Year and Date
      20130313-15
    • Invited
  • [Presentation] 音声対話システムのさらなる普及には何が必要か2013

    • Author(s)
      李 晃伸
    • Organizer
      第95回音声言語情報処理研究会SIG-SLP(第3回対話システムシンポジウム)パネルディスカッション
    • Place of Presentation
      静岡県熱海市
    • Year and Date
      20130201-02
    • Invited
  • [Presentation] Pipeline Decomposition of Speech Decoders and Their Implementation Based on Delayed Evaluation2012

    • Author(s)
      Takahiro Shinozaki
    • Organizer
      APSIPA Annual Summit and Conference 2012
    • Place of Presentation
      Hollywood, California, US
    • Year and Date
      20121203-06
  • [Presentation] Detecting child speaker based on auditory feature vectors for VTL estimation2012

    • Author(s)
      Ryuichi Nisimura
    • Organizer
      APSIPA Annual Summit and Conference 2012
    • Place of Presentation
      Hollywood, California, USA
    • Year and Date
      20121203-06
  • [Presentation] Automatic transcription of lecture speech using language model based on speaking-style transformation of proceeding texts2012

    • Author(s)
      Yuya Akita
    • Organizer
      INTERSPEECH 2012
    • Place of Presentation
      Portland, Oregon, US
    • Year and Date
      20120909-13
  • [Presentation] 音声対話システム技術の現状と課題2012

    • Author(s)
      駒谷和範
    • Organizer
      電気関係学会東海支部連合大会
    • Place of Presentation
      静岡大学
    • Year and Date
      2012-09-25
    • Invited
  • [Presentation] Developing a method to build Japanese speech recognition system based on 3-gram language model expansion with Google database2011

    • Author(s)
      Toshiaki Shimada, Ryuichi Nisimura, Masayasu Tanaka, Hideki Kawahara, Toshio Irino
    • Organizer
      ICISS2011 (2011 IEEE International Conference on Intelligent Computing and Integrated Systems)
    • Place of Presentation
      Guilin, China
    • Year and Date
      2011-10-26
  • [Presentation] Topic-Dependent Language Modeling for VoiceWeb Systems2009

    • Author(s)
      Kentaro Suzuta, Ryuichi Nisimura., et al
    • Organizer
      WESPAC X 2009
    • Place of Presentation
      Beijing, China
    • Year and Date
      2009-09-23
  • [Presentation] Ranking Help Message Candidates Based on Robust Grammar Verification Results and Utterance History in Spoken Dialogue Systems2009

    • Author(s)
      Kazunori Komatani., 他4名
    • Organizer
      10th Annual SIGDIAL Meeting on Discourse and Dialogue
    • Place of Presentation
      London, UK
    • Year and Date
      2009-09-12
  • [Presentation] Automatic Transcription System for Meetings of the Japanese National Congres2009

    • Author(s)
      Yuya Akita
    • Organizer
      ISCA Interspeech 2009
    • Place of Presentation
      Brighton Centre, Brighton, UK
    • Year and Date
      2009-09-07
  • [Presentation] Automatic Transcription System for Meetings of the Japanese National Congress2009

    • Author(s)
      Yuya Akita
    • Organizer
      ISCA Interspeech 2009
    • Place of Presentation
      Brighton Centre, Brighton, UK
    • Year and Date
      2009-09-07
  • [Presentation] Topic-Dependent Language Modeling for VoiceWeb Systems2009

    • Author(s)
      Ryuichi Nisimura
    • Organizer
      HCI International 2009
    • Place of Presentation
      San Diego, CA, US
    • Year and Date
      2009-07-22

URL: 

Published: 2015-06-25  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi