Intonation and Syntax in Spoken Language Systems

Loading...
Thumbnail Image
Penn collection
Technical Reports (CIS)
Degree type
Discipline
Subject
Funder
Grant number
License
Copyright date
Distributor
Related resources
Author
Steedman, Mark J
Contributor
Abstract

Phrasal intonation is notorious for a tendency to perceptually segment the word-string of a spoken utterance into groups which may violate orthodox syntactic notions of constituency. For example, the normal prosody for the answer (b) to the following question (a) imposes the intonational constituency indicated by the brackets (stress, marked in this case by raised pitch, is indicated by capit als) : (1) a. I know that brassicas are a good source of minerals, but what are LEGumes a good source of? b. (LEGumes are a good source of) VITamins . Such a grouping cuts across the traditional syntactic structure of the sentence. The presence of two apparently uncoupled levels of structure in natural language grammar appears to complicate the path from speech to interpretation unreasonably, and to thereby threaten a number of computational applications in speech recognition and and speech synthesis.

Advisor
Date Range for Data Collection (Start Date)
Date Range for Data Collection (End Date)
Digital Object Identifier
Series name and number
Publication date
1989-12-01
Volume number
Issue number
Publisher
Publisher DOI
Journal Issue
Comments
University of Pennsylvania Department of Computer and Information Science Technical Report No. MS-CIS-89-20.
Recommended citation
Collection