Skip to content

Publications

Detail of publication

Citation

Krňoul, Z. and Železný, M. and Müller, L. and Kanis, J. : Training of coarticulation models using dominance functions and visual unit selection methods for audio-visual speech synthesis . Interspeech, vol. 1, p. 585-588, ISCA, Bonn, 2006.

Download PDF

PDF

Abstract

This paper presents results of training of coarticulation models for Czech audio-visual speech synthesis. Two approaches for solution of coarticulation in audio-visual speech synthesis were used, coarticulation based on dominance functions and visual unit selection. For both approaches, coarticulation models were trained. Models for unit selection approach were trained by visualy clustered data. These data were obtained using decision tree algorithm. Outputs of audio-visual speech synthesis for both approaches were assessed and compared objectively.

Detail of publication

Title: Training of coarticulation models using dominance functions and visual unit selection methods for audio-visual speech synthesis
Author: Krňoul, Z. ; Železný, M. ; Müller, L. ; Kanis, J.
Language: English
Date of publication: 17 Sep 2006
Year: 2006
Type of publication: Papers in journals
Title of journal or book: Interspeech
Číslo vydání: 1
Page: 585 - 588
ISBN: 1990-9772
ISSN: 1990-9772
Publisher: ISCA
Address: Bonn
Date: 17 Sep 2006 - 21 Sep 2006
/ 2012-05-25 14:24:41 /

Keywords

audio-visual speech synthesis, talking head, coarticulation model

BibTeX

@ARTICLE{KrnoulZ_2006_Trainingof,
 author = {Kr\v{n}oul, Z. and \v{Z}elezn\'{y}, M. and M\"{u}ller, L. and Kanis, J.},
 title = {Training of coarticulation models using dominance functions and visual unit selection methods for audio-visual speech synthesis},
 year = {2006},
 publisher = {ISCA},
 journal = {Interspeech},
 address = {Bonn},
 volume = {1},
 pages = {585-588},
 ISBN = {1990-9772},
 ISSN = {1990-9772},
 url = {http://www.kky.zcu.cz/en/publications/KrnoulZ_2006_Trainingof},
}