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

讲座演讲自动索引及其通过语音交互的高级利用

基本信息

批准号：
17300064
负责人：
NAKAGAWA Seiichi
金额：
$ 10.26万
依托单位：
Toyohashi University of Technology
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (B)
财政年份：
2005
资助国家：
日本
起止时间：
2005 至 2007
项目状态：
已结题

来源：
https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-17300064/
关键词：
class room lecture speech speech recognition spoken language language model speech summarization indexing speech retrieval brounsing 音声ドキュメント

项目摘要

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

我们收集了16位演讲者、114个讲座、3860分钟的课堂演讲演讲，并发布了语料库。我们开发了自动语音识别、句子提取、分词/索引、口语检索和课堂演讲浏览系统构建的程序。我们大学研究生课程的讲座数据需要提高广播声音或视频数据的可用性。在讲座的情况下，总结和索引讲座演讲或视频使学生能够更多地了解。我们的目标是构建一个此类结构化讲座内容的框架，为了实现这一目标，我们首先研究了录音方法对语音识别性能的影响，结果表明，不同语言之间的准确率存在 23% 的差异。此外，我们通过使用相关的网络文本改进了领域相关的语言模型，并开发了填充插入模型。其次，我们尝试通过提取重要句子进行自动摘要，得到了 0.319- 。 0.456 κ值，与人类的行为相当0.407-0.477 最后，我们利用上述过程的结果构建了使用户能够更有效地学习的讲座浏览系统，并对其进行了评估。