Development of the lecture video retrieval system based on knowledge

我们开发了一个课堂视频检索系统。系统分析视频使用声音识别使用声音识别使用自动语音识别.该系统使我们能够在视频中搜索到所需的场景。通过将客户端系统配置为Web应用程序，现在不仅可以从PC而且可以从移动的终端使用该系统。因此，使用课堂视频的学习效率提高了。利用内容补集和关键词扩展的方法对口语文档检索进行了研究。结果发现，一个开始的副主题是有用的主题信息的内容补充。利用从属概念对检索关键词进行扩展是有效的。子字是有效的，因为在许多情况下，检索关键字不包含在目标中。此外，内容补充、关键词扩展、子词等方法的效果优于单独使用。

We have developed a search system of the class video. The system analyzes the video analyzes the video analyzes the video using sound recognition using sound recognitionusing automatic speech recognition. This system enables us to search the scene that needed in the video. By configuring the client system as a web application, the system is now available from not only PC but also the mobile terminals. Therefore, the learning efficiency using class video increased. The method of spoken document retrieval was examined using the contents complement and keyword expansion. It was found that a beginning subtopic is useful as topic information in the contents complement. The expansion of the retrieval keyword by using the subordinate concept was effective. The subword was effective because a retrieving keyword was not contained in target in many cases. Moreover, the method using the contents complement, keyword expansion, and subword was better than the individual use.