Skip to content

Publications

Detail of publication

Citation

Romportl, J. and Kala, J. : Prosody Modelling in Czech Text-to-Speech Synthesis . Proceedings of the 6th ISCA Workshop on Speech Synthesis, p. 200-205, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, 2007.

Download PDF

PDF

Abstract

This paper describes data-driven modelling of all three basic prosodic features - fundamental frequency, intensity and segmental duration - in the Czech text-to-speech system ARTIC. The fundamental frequency is generated by a model based on concatenation of automatically acquired intonational patterns. Intensity of synthesised speech is modelled by experimentally created rules which are in conformity with phonetics studies. Phoneme duration modelling has not been previously solved in ARTIC and this paper presents the first solution to this problem using a CART-based approach.

Detail of publication

Title: Prosody Modelling in Czech Text-to-Speech Synthesis
Author: Romportl, J. ; Kala, J.
Language: English
Date of publication: 22 Aug 2007
Year: 2007
Type of publication: Papers in proceedings of reviewed conferences
Book title: Proceedings of the 6th ISCA Workshop on Speech Synthesis
Page: 200 - 205
Publisher: Rheinische Friedrich-Wilhelms-Universität Bonn
Address: Bonn
Date: 22 Aug 2007 - 24 Aug 2007
/ 2008-05-19 14:47:27 /

Keywords

prosody, text-to-speech, TTS, synthesis, speech

BibTeX

@INPROCEEDINGS{RomportlJ_2007_ProsodyModellingin,
 author = {Romportl, J. and Kala, J.},
 title = {Prosody Modelling in Czech Text-to-Speech Synthesis},
 year = {2007},
 publisher = {Rheinische Friedrich-Wilhelms-Universit?t Bonn},
 address = {Bonn},
 pages = {200-205},
 booktitle = {Proceedings of the 6th ISCA Workshop on Speech Synthesis},
 url = {http://www.kky.zcu.cz/en/publications/RomportlJ_2007_ProsodyModellingin},
}