ZČU
Publications
Detail of publication
Citation
: Czech audio-visual speech synthesis with an HMM-trained speech database and enhanced coarticulation . WSEAS Transactions on Computers, Vol. 2, vol. 3, p. 733-738, 2003.
Abstract
The task of visual speech synthesis is usually solved by concatenation of basic speech units selected from a visual speech database. There are two main problems in this process. The first problem is a design of a database, that means estimation of the database parameters for all basic speech units. Second problem is a way how to concatenate selected basic phonetic units so as to eliminate the coarticulation effect. Both problems are aimed in our work, resulting in the Czech audio-visual speech synthesizer. We use HMM training process instead of some form of averaging for obtaining statistically best parameters for all basic phonetic units. For solution of a coarticulation effect we use the method of dominance functions.
Detail of publication
| Title: | Czech audio-visual speech synthesis with an HMM-trained speech database and enhanced coarticulation |
|---|---|
| Author: | Železný, M. ; Krňoul, Z. |
| Language: | English |
| Date of publication: | 1 Jan 2003 |
| Year: | 2003 |
| Type of publication: | Papers in journals |
| Title of journal or book: | WSEAS Transactions on Computers |
| Series: | Vol. 2 |
| Číslo vydání: | 3 |
| Page: | 733 - 738 |
| ISBN: | 1109-2750 |
Keywords
talking head, coarticulation, speech corpora, audio-visual speech synthesis, hidden Markov models
BibTeX
@ARTICLE{ZeleznyM_2003_Czechaudio-visual,
author = {\v{Z}elezn\'{y}, M. and Kr\v{n}oul, Z.},
title = {Czech audio-visual speech synthesis with an HMM-trained speech database and enhanced coarticulation},
year = {2003},
journal = {WSEAS Transactions on Computers},
volume = {3},
pages = {733-738},
series = {Vol. 2},
ISBN = {1109-2750},
url = {http://www.kky.zcu.cz/en/publications/ZeleznyM_2003_Czechaudio-visual},
}