Publications
Detail of publication
Citation
p. 3657-3673, 2006. : Design, implementation and evaluation of the Czech realistic audio-visual speech synthesis . Signal Processing, 86, vol. 12,
Additional information
Abstract
This paper presents the whole process of design, implementation and evaluation of the audio-visual speech synthesis system. Such system consists of the acoustic synthesis emulating human speech and the facial animation emulating the human lip articulation. The acoustic speech synthesis is based on concatenation of speech units. The visual subsystem is designed as a realistic, fully three-dimensional parametrically controllable facial animation model. The design, acquisition and processing of audio-visual speech corpus for such purpose is presented. Also, solution to the problem of mapping visual parameters from speech signal either directly or through recognized text is presented. Furthermore, the 3D scanning algorithm is presented. In the end of this paper, evaluation of intelligibility of the presented audio-visual speech synthesis and its possible applications are presented.
Detail of publication
Title: | Design, implementation and evaluation of the Czech realistic audio-visual speech synthesis |
---|---|
Author: | Železný, M. ; Krňoul, Z. ; Císař, P. ; Matoušek, J. |
Language: | English |
Date of publication: | 1 Dec 2006 |
Year: | 2006 |
Type of publication: | Papers in journals |
Title of journal or book: | Signal Processing |
Series: | 86 |
Číslo vydání: | 12 |
Page: | 3657 - 3673 |
ISSN: | 0165-1684 |
Keywords
Audio-visual speech processing, Talking-head, Facial animation
BibTeX
@ARTICLE{ZeleznyM_2006_Design, author = {\v{Z}elezn\'{y}, M. and Kr\v{n}oul, Z. and C\'{i}sa\v{r}, P. and Matou\v{s}ek, J.}, title = {Design, implementation and evaluation of the Czech realistic audio-visual speech synthesis}, year = {2006}, journal = {Signal Processing}, volume = {12}, pages = {3657-3673}, series = {86}, ISSN = {0165-1684}, url = {http://www.kky.zcu.cz/en/publications/ZeleznyM_2006_Design}, }