Robust Unsupervised Audio-Visual Speech Enhancement Using a Mixture of Variational Autoencoders.

Mostafa Sadeghi Xavier Alameda-Pineda

Published in: ICASSP (2020)

Keyphrases

audio visual
multi modal
speech enhancement
noisy environments
visual information
noise reduction
visual data
denoising
multi stream
image processing
signal to noise ratio
multimedia
speech signal
computer vision
pattern recognition
low level
multiscale
gaussian mixture model
information retrieval
audio features