Abstract
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.
Full text
PDF
Selected References
These references are in PubMed. This may not be the complete list of references from this article.
- Bates M. Models of natural language understanding. Proc Natl Acad Sci U S A. 1995 Oct 24;92(22):9977–9982. doi: 10.1073/pnas.92.22.9977. [DOI] [PMC free article] [PubMed] [Google Scholar]
- Levelt W. J. Monitoring and self-repair in speech. Cognition. 1983 Jul;14(1):41–104. doi: 10.1016/0010-0277(83)90026-4. [DOI] [PubMed] [Google Scholar]
- Makhoul J., Schwartz R. State of the art in continuous speech recognition. Proc Natl Acad Sci U S A. 1995 Oct 24;92(22):9956–9963. doi: 10.1073/pnas.92.22.9956. [DOI] [PMC free article] [PubMed] [Google Scholar]