Audio-Visual Speech Inpainting with Deep Learning.

Giovanni Morrone Daniel Michelsanti Zheng-Hua Tan Jesper Jensen

Published in: ICASSP (2021)

Keyphrases

audio visual
deep learning
multi modal
unsupervised learning
multi stream
visual information
emotion recognition
machine learning
audio visual speech recognition
mental models
multimedia
visual data
weakly supervised
image processing
supervised learning
low level
high dimensional
training data
three dimensional