A Speech-First Model for Repair Detection and Correction
A Speech-First Model for Repair Detection and Correction
复制标题
用于修复检测和纠正的语音优先模型
DOI：
10.3115/981574.981581
复制
发表时间：
1993
期刊：
影响因子：
--
通讯作者：
Julia Hirschberg
中科院分区：
文献类型：
--
作者：
C. Nakatani;Julia Hirschberg
翻译完全自然的语音是口语理解系统的一个重要目标。然而，尽管语料库研究表明，大约10%的自发话语包含自我纠正或修复，但人们对语音信号中的线索在多大程度上有助于修复处理知之甚少。我们基于对DARPA航空旅行信息系统数据库中维修的声学和韵律分析识别了几个线索，并提出了利用这些线索检测和纠正维修的方法。
Interpreting fully natural speech is an important goal for spoken language understanding systems. However, while corpus studies have shown that about 10% of spontaneous utterances contain self-corrections, or REPAIRS, little is known about the extent to which cues in the speech signal may facilitate repair processing. We identify several cues based on acoustic and prosodic analysis of repairs in the DARPA Air Travel Information System database, and propose methods for exploiting these cues to detect and correct repairs.