首页> 外文OA文献 >Prosodic scoring of word hypotheses graphs
【2h】

Prosodic scoring of word hypotheses graphs

机译:单词假设图的韵律评分

代理获取
本网站仅为用户提供外文OA文献查询和代理获取服务,本网站没有原文。下单后我们将采用程序或人工为您竭诚获取高质量的原文,但由于OA文献来源多样且变更频繁,仍可能出现获取不到、文献不完整或与标题不符等情况,如果获取不到我们将提供退款服务。请知悉。
获取外文期刊封面目录资料

摘要

Prosodic boundary detection is important to disambiguate parsing, especially in spontaneous speech, where elliptic sentences occur frequently. Word graphs are an efficient interface between word recognition and parser. Prosodic classification of word chains has been published earlier. The adjustments necessary for applying these classification techniques to word graphs are discussed in this paper. When classifying a word hypothesis a set of context words has to be determined appropriately. A method has been developed to use stochastic language models for prosodic classification. This as well has been adopted for the use on word graphs. We also improved the set of acoustic-prosodic features with which the recognition errors were reduced by about 60% on the read speech we were working on previously, now achieving 10% error rate for 3 boundary classes and 3% for 2 accent classes. Moving to spontaneous speech the recognition error increases significantly (e.g. 16% for a 2-class boundary task). We show that even on word graphs the combination of language models which model a larger context with acoustic-prosodic classifiers reduces the recognition error by up to 50 %.
机译:韵律边界检测对于消除歧义解析非常重要,尤其是在经常出现椭圆句子的自发​​语音中。字图是单词识别和解析器之间的有效接口。单词链的韵律分类早已发布。本文讨论了将这些分类技术应用于单词图的必要调整。在对单词假设进行分类时,必须适当地确定一组上下文单词。已经开发出一种用于将随机语言模型用于韵律分类的方法。这也已被用于单词图。我们还改进了声学韵律功能集,通过这些功能,我们之前正在阅读的语音的识别错误减少了约60%,现在对于3个边界类别,实现了10%的错误率,对于2种重音类别,实现了3%的错误率。转向自发语音时,识别错误显着增加(例如,对于2类边界任务而言为16%)。我们表明,即使在单词图上,使用声韵分类器对较大上下文进行建模的语言模型组合也可以将识别错误降低多达50%。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号