Training of coarticulation models using dominance functions and visual unit selection methods for audio-visual speech synthesis

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F49777513%3A23520%2F06%3A00500111" target="_blank" >RIV/49777513:23520/06:00500111 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Training of coarticulation models using dominance functions and visual unit selection methods for audio-visual speech synthesis
Original language description
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.
Czech name
—
Czech description
—

Project
<a href="/en/project/1ET101470416" target="_blank" >1ET101470416: Multimodal human sign language and speech processing for man-machine communication</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2006
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Interspeech 2006 and 9th International Conference on Spoken Language Processing
ISBN
978-1-60423-449-7
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
—
Publisher name
Curran Associates
Place of publication
New York
Event location
Pittsburgh
Event date
Sep 21, 2006
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
000269965900147

Similar results(10)