On the Use of Automatically Generated Discourse-Level Information in a Concept-to-Speech Synthesis System

Edinburgh Research Archive

Please use this identifier to cite or link to this item: http://hdl.handle.net/1842/1013

This item has been viewed 16 times in the last year. View Statistics

Files in This Item:

File	Description	Size	Format
Hitzeman_1998_d.pdf		41.24 kB	Adobe PDF	View/Open

Title:	On the Use of Automatically Generated Discourse-Level Information in a Concept-to-Speech Synthesis System
Authors:	Hitzeman, Janet Black, Alan W Taylor, Paul Mellish, Chris Oberlander, Jon
Issue Date:	Dec-1998
Citation:	In ICSLP-1998, paper 0591.
Publisher:	International Speech Communication Association
Abstract:	This paper describes the latest version of the SOLE concept-to-speech system, which uses linguistic information provided by a natural language generation system to improve the prosody of synthetic speech. We discuss the types of linguistic information that prove most useful and the implications for text-to-speech systems.
URI:	http://www.isca-speech.org/archive/icslp_1998/index.html http://hdl.handle.net/1842/1013
Appears in Collections:	CSTR publications