Development of self-study lecture video retrieval system using integrated knowledge

2016 Fiscal Year Final Research Report

• Project/Area Number: 26350355
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Educational technology
• Research Institution: Ishikawa National College of Technology
• Principal Investigator: KANEDERA Noboru 石川工業高等専門学校, その他部局等, 教授 (50194931)
• Project Period (FY): 2014-04-01 – 2017-03-31
• Keywords: 教材情報システム / 音声情報内容検索 / シーンベクトルの線形補間 / 音声認識 / 講義ビデオ

Outline of Final Research Achievements

Along with increased multimedia information with spoken content, spoken document retrieval has attracted attention. Therefore, we developed a system that can register and retrieve videos, including lecture videos. This system extracts spoken content from videos and converts it to text by automatic speech recognition, this text can be targeted by queries. This system can also retrieve video scenes similar to the scenes currently being viewed.
We confirmed the linear interpolation is effective in related spoken document retrieval, where the linear interpolation use first subtopic and whale subtopic in the each video. We also reveal the relationship between speech recognition performance and related spoken document retrieval performance.

Free Research Field

総合領域