Sign in
Multi-Stream Gated and Pyramidal Temporal Convolutional Neural Networks for Audio-Visual Speech Separation in Multi-Talker Environments.
Yiyu Luo
Jing Wang
Liang Xu
Lidong Yang
Published in:
Interspeech (2021)
Keyphrases
</>
audio visual speech recognition
multi stream
convolutional neural networks
visual speech
audio visual
hidden markov models
sound source
spatio temporal
multiresolution
multi modal
noisy environments
non stationary
speaker identification
audio signal