Cogans For Unsupervised Visual Speech Adaptation To New Speakers.

Adriana Fernandez-Lopez Ali Karaali Naomi Harte Federico M. Sukno

Published in: ICASSP (2020)

Keyphrases

visual speech
visual speech recognition
speech recognition
hidden markov models
person authentication
unsupervised learning
lip reading
semi supervised
speaker identification
multi modal
multiscale
multiresolution
noisy environments