From interlingua to speech: generating prosodic information from conceptual representation

Author

Sakai, Shinsuke ; Muraki, Kazunori

Author_Institution

NEC Corp., Kawasaki, Japan

fYear

1990

fDate

3-6 Apr 1990

Firstpage

329

Abstract

A method for generating prosodic information for speech synthesis from conceptual representation is presented. A computational model of generating prosodic information from pragmatic, semantic, syntactic, and lexical information of the utterance is proposed. The various types of information are computed using the information extracted from the conceptual representation and the lexicon through the process of uttered sentence generation. An experimental system for speech synthesis from conceptual representation is developed, and better prosodic quality is obtained than with conventional synthetic speech, according to an informal listening test

Keywords

speech intelligibility; speech recognition; speech synthesis; computational model; conceptual representation; informal listening test; lexical information; lexicon; pragmatic information; prosodic information; prosodic quality; semantic information; speech synthesis; syntactic information; utterance; uttered sentence generation; Computational modeling; Data mining; Information technology; Laboratories; National electric code; Natural languages; Spatial databases; Speech analysis; Speech synthesis; Stress control; System testing; Testing;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1990. ICASSP-90., 1990 International Conference on

Conference_Location

Albuquerque, NM

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1990.115666

Filename

115666