Skip to content

Publications

Detail of publication

Citation

Romportl, J. : Structural Data-Driven Prosody Model for TTS Synthesis . Proceedings of the Speech Prosody 2006 Conference, p. 549-552, TUDpress, Dresden, 2006.

Download PDF

PDF

Abstract

This paper introduces a new data-driven prosody model for the text-to-speech system ARTIC. The model is intended to be almost language-independent and to generate naturally sounding intonation with a link to semantics. It is based on text parametrisation using a new prosodic grammar and on automatic speech corpora analysis methods. Its performance is evaluated by results of presented listening tests.

Detail of publication

Title: Structural Data-Driven Prosody Model for TTS Synthesis
Author: Romportl, J.
Language: English
Date of publication: 2 May 2006
Year: 2006
Type of publication: Papers in proceedings of reviewed conferences
Book title: Proceedings of the Speech Prosody 2006 Conference
Page: 549 - 552
ISBN: 0940-6832
ISSN: 0940-6832
Publisher: TUDpress
Address: Dresden
Date: 2 May 2006 - 5 May 2006
/ 2008-05-19 15:42:14 /

Keywords

prosody, text-to-speech, TTS, grammar, model

BibTeX

@INPROCEEDINGS{RomportlJ_2006_Structural,
 author = {Romportl, J.},
 title = {Structural Data-Driven Prosody Model for TTS Synthesis},
 year = {2006},
 publisher = {TUDpress},
 address = {Dresden},
 pages = {549-552},
 booktitle = {Proceedings of the Speech Prosody 2006 Conference},
 ISBN = {0940-6832},
 ISSN = {0940-6832},
 url = {http://www.kky.zcu.cz/en/publications/RomportlJ_2006_Structural},
}