Multimodal attention for lip synthesis using conditional generative adversarial networks.

Andrea Vidal Carlos Busso

Published in: Speech Commun. (2023)

Keyphrases

generative model
multi modal
network analysis
program synthesis
unsupervised learning
social networks
visual attention
network topologies
network structure
network model
complex networks
utility independence
multimodal interaction
audio visual
data driven
multi agent
multimedia