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

Automatic indexing for lecture speech and its advanced utilization through speech interaction

Research Project

Project/Area Number 17300064
Research Category

Grant-in-Aid for Scientific Research (B)

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

Principal Investigator

NAKAGAWA Seiichi  Toyohashi University of Technology, Faculty of Engineering, Professor (20115893)

Co-Investigator(Kenkyū-buntansha) AKIBA Tomoyoshi  University of Technology, Faculty of Engineering, Assistant Professor (00356346)
TSUCHIYA Masatoshi  Toyohashi University of Technology, Faculty of Engineering, Associate Professor (70378256)
KITAOKA Norihide  Nagoya University, Graduate School of Information Science, Asscoiate Professor (10333501)
KOGURE Satoru  Shizuoka University, Faculty of Engineering, Associate Professor (40359758)
NISHIZAKI Hiromitsu  University of Yamanashi, Faculty of engineering, Associate Professor (40362082)
Project Period (FY) 2005 – 2007
Project Status Completed (Fiscal Year 2007)
Budget Amount *help
¥16,030,000 (Direct Cost: ¥14,800,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2007: ¥5,330,000 (Direct Cost: ¥4,100,000、Indirect Cost: ¥1,230,000)
Fiscal Year 2006: ¥3,900,000 (Direct Cost: ¥3,900,000)
Fiscal Year 2005: ¥6,800,000 (Direct Cost: ¥6,800,000)
Keywordsclass room lecture speech / speech recognition / spoken language / language model / speech summarization / indexing / speech retrieval / brounsing / 音声ドキュメント
Research Abstract

We collected the class room lecture speech consisting of 16 speakers, 114 lectures, and 3860 minutes, and publised the corpus. We developed the procedure of automatic speech recognition, sentence extraction, segmentation/indexing, spoken retrieval and construction of lecture browsing system for classroom lecture data of our university's graduated course. These processes axe necessary to improve the usability of broadcasting sound or video data In the case of lecture, summarized and indexed lecture speech or video enables to students to more effective leaning. Our goal was to construct a framework of such structured lecture contents. To achieve this goal, first, we investigated influence of the recording methods on the speech recognition performance. It turned out that there was 23% difference on the accuracy between a high quality hand-microphone and a low quality lapel microphone. Furthermore, we improved the domain-dependent language model by using related Web texts and developed a filler insertion model. Second, we tried automatic summarization by extracting important sentences, and we obtained 0.319-0.456 κ value, comparable with human doing 0.407-0.477. Finally, we constructed the lecture browsing system which enables users to learn more effectively by using results of the procedure described above, and evaluated it

Report

(4 results)
  • 2007 Annual Research Report   Final Research Report Summary
  • 2006 Annual Research Report
  • 2005 Annual Research Report
  • Research Products

    (30 results)

All 2008 2007 2006 2005 Other

All Journal Article (15 results) (of which Peer Reviewed: 1 results) Presentation (13 results) Book (1 results) Remarks (1 results)

  • [Journal Article] 講義音声ドキュメントのコンテンツ化と視聴システム2008

    • Author(s)
      中川聖一, 富樫慎吾, 山口優, 藤井康寿, 北岡教英
    • Journal Title

      電子情報通信学会論文誌 Vol.91-D

      Pages: 238-249

    • NAID

      110007385909

    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2007 Final Research Report Summary
  • [Journal Article] Useful Contents of Classroom Lecture Speech and Browsing System(in Japanese)2008

    • Author(s)
      S. Nakagawa, S. Togashi, M. Yamaguchi, Y. Fujii N. Kitaoka
    • Journal Title

      IEICE Trans. Information and Systerns J91-D, 2

      Pages: 238-248

    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2007 Final Research Report Summary
  • [Journal Article] 講義音声ドキュメンのコンテンツ化と視聴システム2008

    • Author(s)
      中川 聖一, 富樫 慎吾, 山口 優, 藤井 康寿, 北岡 教英
    • Journal Title

      電子情報通信学会論文誌 Vol. 91-D

      Pages: 238-249

    • Related Report
      2007 Annual Research Report
    • Peer Reviewed
  • [Journal Article] 機械学習を用いた日本語機能表現のチャンキング2007

    • Author(s)
      土屋雅稔, 注連隆夫, 高木俊宏, 内元清貴, 松吉俊, 宇津呂武仁, 佐藤理史, 中川聖一
    • Journal Title

      自然言語処理 Vol.14 No.1

      Pages: 111-138

    • NAID

      10018504343

    • Related Report
      2006 Annual Research Report
  • [Journal Article] 講義ドキュメントのコンテンツ化と視聴システムの試作2007

    • Author(s)
      富樫慎吾, 藤井康寿, 北岡教英, 中川聖一
    • Journal Title

      第1回音声ドキュメント処理ワークショップ講演論文集

      Pages: 17-24

    • Related Report
      2006 Annual Research Report
  • [Journal Article] 講義コンテンツの収集・分析および講義音声の認識手法に関する検討2007

    • Author(s)
      小暮悟, 西崎博光, 土屋雅稔, 中川聖一
    • Journal Title

      第1回音声ドキュメント処理ワークショップ講演論文集

      Pages: 1-8

    • NAID

      40016334727

    • Related Report
      2006 Annual Research Report
  • [Journal Article] 日本語複合辞書用例データベースの作成と分析2006

    • Author(s)
      土屋雅稔, 宇津呂武仁, 松吉俊, 佐藤理史, 中川聖一
    • Journal Title

      情報処理学会論文誌 47(6)

      Pages: 1728-1742

    • Related Report
      2006 Annual Research Report
  • [Journal Article] Robust Distant Speech Recognition by Combining Multiple Microhone-array Processing with Position Dependent CMN2006

    • Author(s)
      L.Wang, N.Kitaoka, S.Nakagawa
    • Journal Title

      Eurasip Journal on Applied Signal Processing (95491)

      Pages: 1-11

    • Related Report
      2006 Annual Research Report
  • [Journal Article] 音声対話機能を備えた音色識別学習支援システム2006

    • Author(s)
      渡辺裕太, 瀾口芳廣, 西崎博光
    • Journal Title

      情報処理学会論文誌 Vol.42 No.12

      Pages: 3173-3184

    • NAID

      110004729743

    • Related Report
      2006 Annual Research Report
  • [Journal Article] Text-independent/text-prompted speaker recognition by combining speaker-specific GMM with speaker adapted syllable-based HMM2006

    • Author(s)
      S.Nakagawa, W.Zhang, M.Takahashi
    • Journal Title

      Trans.IEICE, Information & Systems Vol.E89-D No.3

    • NAID

      110004719381

    • Related Report
      2005 Annual Research Report
  • [Journal Article] Response timing detection using prosodic and linguistic information for human-freindly spoken dialog systems2005

    • Author(s)
      N.Kitaoka, M.Takeuchi, R.Nishimura, S.Nakagawa
    • Journal Title

      人工知能学会論文誌 Vol.20, No.3

      Pages: 220-228

    • Related Report
      2005 Annual Research Report
  • [Journal Article] フォーム型Web情報検索サービスのための音声ユーザインタフェースシステムと操作性の評価2005

    • Author(s)
      甲斐充彦, 盛浩和, 仲野崇広, 中川聖一
    • Journal Title

      情報処理学会論文誌 Vol.46, No.5

      Pages: 1319-1329

    • NAID

      110002768637

    • Related Report
      2005 Annual Research Report
  • [Journal Article] 日英関連報道記事を用いた訳語対応推定2005

    • Author(s)
      宇津呂武彦, 日野浩平, 堀内貴司, 中川聖一
    • Journal Title

      自然言語処理 Vol.12, No.5

      Pages: 43-68

    • NAID

      130004291858

    • Related Report
      2005 Annual Research Report
  • [Journal Article] 表層的言語情報と韻律情報を用いた講演音声の重要文抽出2005

    • Author(s)
      小林聡, 山口優, 中川聖一
    • Journal Title

      自然言語処理 Vol.12, No.6

      Pages: 3-23

    • NAID

      10016863571

    • Related Report
      2005 Annual Research Report
  • [Journal Article] CALLと音声情報処理技術2005

    • Author(s)
      中川聖一
    • Journal Title

      音声研究 Vol.9, No.2

      Pages: 28-37

    • Related Report
      2005 Annual Research Report
  • [Presentation] フィラー予測モデルを用いた話し言葉言語モデルの音声認識による評価2008

    • Author(s)
      太田健吾, 土屋雅稔, 中川聖一
    • Organizer
      第2回音声ドキュメント処理ワークショップ講演論文集
    • Place of Presentation
      豊橋
    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2007 Annual Research Report 2007 Final Research Report Summary
  • [Presentation] 講義音声ドキュメントのコンテンツ化とブラウジングシステムの改良2008

    • Author(s)
      富樫慎吾, 中川聖一
    • Organizer
      第2回音声ドキュメント処理ワークショップ講演論文集
    • Place of Presentation
      豊橋
    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2007 Annual Research Report 2007 Final Research Report Summary
  • [Presentation] 日本語講義音声コンテンツコーパスの構築と講義音声認識手法の検討2008

    • Author(s)
      小暮悟, 西崎博光, 土屋雅稔, 富樫慎吾, 山本一公, 中川聖一
    • Organizer
      第2回音声ドキュメント処理ワークショップ講演論文集
    • Place of Presentation
      豊橋
    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2007 Annual Research Report 2007 Final Research Report Summary
  • [Presentation] 講義音声認識のためのWEB文書を用いた言語モデルの適応化と語彙選択2008

    • Author(s)
      徳田翔, 西崎博光, 関口芳廣
    • Organizer
      第2回音声ドキュメント処理ワークショップ講演論文集
    • Place of Presentation
      豊橋
    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2007 Annual Research Report 2007 Final Research Report Summary
  • [Presentation] 講義音声の自動評価のための各種特徴量の調査2008

    • Author(s)
      小林健司, 宗宮充宏, 名取賢, 西崎博光
    • Organizer
      第2回音声ドキュメント処理ワークショップ講演論文集
    • Place of Presentation
      豊橋
    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2007 Annual Research Report 2007 Final Research Report Summary
  • [Presentation] 固有表現検出を用いた認識誤りに頑健な音声ドキュメント質問応答2008

    • Author(s)
      秋葉友良, 辻村裕史
    • Organizer
      第2回音声ドキュメント処理ワークショップ講演論文集
    • Place of Presentation
      豊橋
    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2007 Annual Research Report 2007 Final Research Report Summary
  • [Presentation] 認識候補から正解テキストへの翻訳モデルに基づく講演音声ドキュメントのアドホック検索2008

    • Author(s)
      秋葉友良, 横田悠右
    • Organizer
      第2回音声ドキュメント処理ワークショップ講演論文集
    • Place of Presentation
      豊橋
    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2007 Annual Research Report 2007 Final Research Report Summary
  • [Presentation] LVCSR based on context dependent syllable acoustic models2008

    • Author(s)
      J. Zhang, L. Wang, S. Nakagawa
    • Organizer
      Proc. Asian workshop on Speech Science and Technology
    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2007 Final Research Report Summary
  • [Presentation] 講義音声収録映像の音声情報を用いた講義コンテンツの構築と評価2007

    • Author(s)
      富樫慎吾, 中川聖一
    • Organizer
      日本音響学会 秋季講演論文集
    • Place of Presentation
      甲府
    • Description
      「研究成果報告書概要(和文)」より
    • Related Report
      2007 Final Research Report Summary
  • [Presentation] Construction of spoken language model including fillers using filler prediction model2007

    • Author(s)
      K. Ohta, M. Tsuchiya, S. Nakagawa
    • Organizer
      Proc. InterSpeech
    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2007 Final Research Report Summary
  • [Presentation] Automatic extraction of the phrases for important sentences in lecture speech and automatic lecture speech summarization2007

    • Author(s)
      Y. Fujii, N. Kitaoka, S. Nakagawa
    • Organizer
      Proc. InterSpeech
    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2007 Final Research Report Summary
  • [Presentation] Error-tolerant question answering for spoken documents2007

    • Author(s)
      T. Akiba, H. Tsujimura
    • Organizer
      Proc. InterSpeech
    • Description
      「研究成果報告書概要(欧文)」より
    • Related Report
      2007 Final Research Report Summary
  • [Presentation] 講義音声収録映像の音声情報を用いた講義コンテンツの構築と評価2007

    • Author(s)
      富樫 慎吾, 中川 聖一
    • Organizer
      日本音響学会秋季講演論文集
    • Place of Presentation
      甲府
    • Related Report
      2007 Annual Research Report
  • [Book] Spoken Language Systems2005

    • Author(s)
      S.Nakagawa, M.Okada, T.Kawahara
    • Total Pages
      347
    • Publisher
      Ohmsha, IOS Press
    • Related Report
      2005 Annual Research Report
  • [Remarks] 「研究成果報告書概要(和文)」より

    • URL

      http://www.slp.ics.tut.ac.jp/CJLC/

    • Related Report
      2007 Final Research Report Summary

URL: 

Published: 2005-04-01   Modified: 2016-04-21  

Information User Guide FAQ News Terms of Use Attribution of KAKENHI

Powered by NII kakenhi