Audio-visual Speech Separation with Adversarially Disentangled Visual Representation.

Peng Zhang Jiaming Xu Jing Shi Yunzhe Hao Bo Xu

Published in: CoRR (2020)

Keyphrases

audio visual
visual representation
multi modal
sound source
visual representations
visual information
multi stream
user interface
visual data
emotion recognition
speaker verification
multimedia
person authentication
human computer interaction
audio features
visual features
expert systems
pattern recognition