From Inference to Generation: End-to-end Fully Self-supervised Generation of Human Face from Speech.

Hyeong-Seok Choi Changdae Park Kyogu Lee

Published in: CoRR (2020)

Keyphrases

end to end
human faces
facial expressions
face detection
data sets
face recognition
high quality
feature points
facial expression recognition
wireless ad hoc networks
real world
three dimensional
similarity measure
facial images
active appearance models