Segmenting Conversations by Topic, Initiative, and Style
Segmenting Conversations by Topic, Initiative, and Style
复制标题
按主题、主动性和风格细分对话
DOI：
10.1007/3-540-45637-6_5
复制
发表时间：
2001
影响因子：
3.5
通讯作者：
K. Ries
中科院分区：
文献类型：
--
作者：
K. Ries
主题切分是对会议录音和其他类型的含有多个主题的较长语音文档进行信息获取的基本工具。标准的分段算法通常基于关键字、音高轮廓或停顿。这项工作表明，扬声器的主动性和风格可以作为分割标准以及。一个概率分割过程，它允许这些功能的集成和建模在一个干净的框架，具有良好的效果。基于关键词的分割方法显着降低我们的会议数据库时，语音识别成绩单，而不是手动成绩单。说话人主动性是一个有趣的功能，因为它提供了良好的分割，应该很容易从音频中获得。在主题的开始、中间和结尾处的语音风格变化也可以被用于主题分割，并且不需要检测稀有关键字。
Topical segmentation is a basic tool for information access to audio records of meetings and other types of speech documents which may be fairly long and contain multiple topics. Standard segmentation algorithms are typically based on keywords, pitch contours or pauses. This work demonstrates that speaker initiative and style may be used as segmentation criteria as well. A probabilistic segmentation procedure is presented which allows the integration and modeling of these features in a clean framework with good results.Keyword based segmentation methods degrade significantly on our meeting database when speech recognizer transcripts are used instead of manual transcripts. Speaker initiative is an interesting feature since it delivers good segmentations and should be easy to obtain from the audio. Speech style variation at the beginning, middle and end of topics may also be exploited for topical segmentation and would not require the detection of rare keywords.
(3) 阐明胎生鱼为未出生的孩子提供的营养
DOI：
--
发表时间：
--
期刊：
影响因子：
--
作者：
通讯作者：
--