Moore R C
Artificial Intelligence Center, SRI International, Menlo Park, CA 94025, USA.
Proc Natl Acad Sci U S A. 1995 Oct 24;92(22):9983-8. doi: 10.1073/pnas.92.22.9983.
The integration of speech recognition with natural language understanding raises issues of how to adapt natural language processing to the characteristics of spoken language; how to cope with errorful recognition output, including the use of natural language information to reduce recognition errors; and how to use information from the speech signal, beyond just the sequence of words, as an aid to understanding. This paper reviews current research addressing these questions in the Spoken Language Program sponsored by the Advanced Research Projects Agency (ARPA). I begin by reviewing some of the ways that spontaneous spoken language differs from standard written language and discuss methods of coping with the difficulties of spontaneous speech. I then look at how systems cope with errors in speech recognition and at attempts to use natural language information to reduce recognition errors. Finally, I discuss how prosodic information in the speech signal might be used to improve understanding.
语音识别与自然语言理解的整合引发了诸多问题，比如如何使自然语言处理适应口语的特点；如何处理错误的识别输出，包括利用自然语言信息来减少识别错误；以及如何利用语音信号中的信息（不仅仅是单词序列）来辅助理解。本文回顾了由美国国防部高级研究计划局（ARPA）赞助的口语项目中针对这些问题的当前研究。我首先回顾一些自发口语与标准书面语言不同的方式，并讨论应对自发语音困难的方法。然后我将探讨系统如何处理语音识别中的错误，以及利用自然语言信息减少识别错误的尝试。最后，我将讨论语音信号中的韵律信息如何用于提高理解。
