A syntax based grammar of stress sequences

Author

Arnfiel, Simon C. ; Atwel, Eric S.

Author_Institution

Div. of Artificial Intelligence, Leeds Univ., UK

fYear

1993

fDate

22-23 Apr 1993

Abstract

The Spoken English Corpus (SEC) is a speech corpus containing prosodic and syntactic annotations and provides an ideal source for the study of the relationship between prosody and syntax. It is shown that the placement of stresses on words in an utterance may be largely predicted from word classifications. The language model used to make these predictions is inferred from the SEC training set. However, it is unlikely that the predictions will be 100% accurate since stress is also a function of context and semantics

Keywords

computational linguistics; grammars; speech analysis and processing; SEC training set; Spoken English Corpus; language model; prosody; speech corpus; stress sequences; syntactic annotations; syntax based grammar; word classifications;

fLanguage

English

Publisher

iet

Conference_Titel

Grammatical Inference: Theory, Applications and Alternatives, IEE Colloquium on

Conference_Location

Colchester

Type

conf

Filename

243122

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=286261