Automatic indexing of lecture presentations using unsupervised learning of presumed discourse markers
Automatic indexing of lecture presentations using unsupervised learning of presumed discourse markers
复制标题
DOI：
10.1109/tsa.2004.828701
复制
发表时间：
2004-06
期刊：
影响因子：
--
通讯作者：
Tatsuya Kawahara;Masahiro Hasegawa;Kazuya Shitaoka;T. Kitade;H. Nanjo
中科院分区：
文献类型：
--
作者：
Tatsuya Kawahara;Masahiro Hasegawa;Kazuya Shitaoka;T. Kitade;H. Nanjo
提出了一种从演讲音频档案中自动检测段落边界和提取关键句的新方法。该方法利用了话语标记语（DM），这是用于初始话语的部分，连同停顿和语言模型信息的特征表达。DM是基于单词统计以完全无监督的方式导出的。使用语料库的自发日语（CSJ）的实验评估表明，该方法提供了更好的索引的部分边界相比，一个简单的基线方法，仅使用暂停信息，它是强大的语音识别错误。该方法也适用于提取关键句，可以索引的部分主题。假设话语标记的统计数据被用来定义句子的重要性，这有利于潜在的节首的。该测度还与传统的基于内容词的tf-idf测度相结合。实验结果证实了DM与基于关键词的方法相结合的有效性。本文还描述了一个统计框架，用于将原始语音转换为文档风格，以定义适当的句子单元并提高可读性。
A new method for automatic detection of section boundaries and extraction of key sentences from lecture audio archives is proposed. The method makes use of 'discourse markers' (DMs), which are characteristic expressions used in initial utterances of sections, together with pause and language model information. The DMs are derived in a totally unsupervised manner based on word statistics. An experimental evaluation using the Corpus of Spontaneous Japanese (CSJ) demonstrates that the proposed method provides better indexing of section boundaries compared with a simple baseline method using pause information only, and that it is robust against speech recognition errors. The method is also applied to extraction of key sentences that can index the section topics. The statistics of the presumed DMs are used to define the importance of sentences, which favors potentially section-initial ones. The measure is also combined with the conventional tf-idf measure based on content words. Experimental results confirm the effectiveness of using the DMs in combination with the keyword-based method. The paper also describes a statistical framework for transforming raw speech transcriptions into the document style for defining appropriate sentence units and improving readability.