Audio-Visual Speech Inpainting with Deep Learning.

Giovanni Morrone Daniel Michelsanti Zheng-Hua Tan Jesper Jensen

Published in: CoRR (2020)

Keyphrases

audio visual
deep learning
multi modal
visual information
unsupervised learning
multi stream
visual data
machine learning
multimedia
emotion recognition
weakly supervised
audio visual speech recognition
mental models
supervised learning
object recognition
video sequences
image processing
e learning
data sets