Development of spoken language processing techniques for real-time captioning on the basis of readability

2010 Fiscal Year Final Research Report

• Project/Area Number: 21700157
• Research Category: Grant-in-Aid for Young Scientists (B)
• Allocation Type: Single-year Grants
• Research Field: Intelligent informatics
• Research Institution: Nagoya University
• Principal Investigator: OHNO Tomohiro Nagoya University, 国際開発研究科, 助教 (20402472)
• Research Collaborator: MURATA Masaki 名古屋大学, 大学院・情報科学研究科, 博士課程後期課程
• Project Period (FY): 2009 – 2010
• Keywords: 音声言語処理 / 係り受け解析 / 整形処理 / 改行処理

Research Abstract

In this research, I developed the following three spoken language processing techniques as elemental techniques for generating readable captions to support the real-time understanding of spoken monologues such as lectures and commentaries : (1) Incremental dependency parsing technique of spoken language based on clause-start identification (2) Text formatting technique (mainly, comma insertion technique) of spoken language based on dependency structure to translate spoken language to readable texts (3) Linefeed insertion technique based on dependency structure to display caption texts in an easy-to-read manner.

Research Products

• [Journal Article] Linefeed Insertion Rules for Improving Readability of Lecture Transcript (2010)
  • Author(s): Masaki Murata, Tomohiro Ohno, Shigeki Matsubara
  • Journal Title: International Journal of Knowledge and Web Intelligence Vol.1, No.3/4 Pages: 227-242
  • Peer Reviewed
• [Journal Article] 読みやすい字幕生成のための講演テキストへの改行挿入 (2009)
  • Author(s): 村田匡輝, 大野誠寛, 松原茂樹
  • Journal Title: 電子情報通信学会論文誌 Vol.J92-D, No.9 Pages: 1621-1631
  • Peer Reviewed
• [Journal Article] Text-Style Conversion of Speech Transcript into Web Document for Lecture Archive (2009)
  • Author(s): Masashi Ito, Tomohiro Ohno, Shigeki Matsubara
  • Journal Title: Journal of Advanced Computational Intelligence and Intelligent Informatics Vol.13, No.4 Pages: 499-505
  • Peer Reviewed
• [Presentation] Automatic Comma Insertion for Japanese Text Generation (2010)
  • Author(s): Masaki Murata, Tomohiro Ohno, Shigeki Matsubara
  • Organizer: the 2010 Conference on Empirical Methods in Natural Language Processing (EMNLP2010)
  • Place of Presentation: アメリカ・ボストン・マサチューセッツ工科大学
  • Year and Date: 2010-10-10
• [Presentation] 読点の用法的分類に基づく自動読点挿入 (2010)
  • Author(s): 村田匡輝, 大野誠寛, 松原茂樹
  • Organizer: 情報処理学会音声言語情報処理研究会
  • Place of Presentation: 東京工業大学
  • Year and Date: 2010-05-27
• [Presentation] 日本語テキストにおける読点位置の検出 (2010)
  • Author(s): 村田匡輝, 大野誠寛, 松原茂樹
  • Organizer: 言語処理学会第16回年次大会
  • Place of Presentation: 東京大学
  • Year and Date: 2010-03-10
• [Presentation] Linefeed Insertion into Japanese Spoken Monologue for Captioning (2009)
  • Author(s): Tomohiro Ohno, Masaki Murata, Shigeki Matsubara
  • Organizer: Joint Conference of the 47th Annual Meeting of the Association for Computational Linguistics and the 4th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing (ACL-IJCNLP2009)
  • Place of Presentation: シンガポール・サンテック市・Suntec Singapore International Convention & Exhibition Centre
  • Year and Date: 2009-08-04
• [Presentation] Automatic Linefeed Insertion for Improving Readability of Lecture Transcript (2009)
  • Author(s): Masaki Murata, Tomohiro Ohno, Shigeki Matsubara
  • Organizer: the 2nd International Symposium on Intelligent Interactive Multimedia Systems and Services (IIMSS-2009)
  • Place of Presentation: イタリア・Mogliano Veneto・VILLA BRAIDAホテル
  • Year and Date: 2009-07-17
• [Presentation] 読みやすい字幕生成のための講演文への漸進的改行挿入 (2009)
  • Author(s): 村田匡輝, 大野誠寛, 松原茂樹
  • Organizer: 情報処理学会情報処理学会音声言語情報処理研究会
  • Place of Presentation: 東京工業大学
  • Year and Date: 2009-05-21
• [Remarks] ホームページ等
  • URL: http://slp.itc.nagoya-u.ac.jp/~ohno/kaken/readable-caption/