Login / Signup
Deep Learning Based Audio-Visual Multi-Speaker DOA Estimation Using Permutation-Free Loss Function.
Qing Wang
Hang Chen
Ya Jiang
Zhe Wang
Yuyang Wang
Jun Du
Chin-Hui Lee
Published in:
ISCSLP (2022)
Keyphrases
</>
audio visual
loss function
deep learning
doa estimation
multi modal
sound source
pairwise
visual information
unsupervised learning
multimedia
support vector
visual data
machine learning
canonical correlation analysis
data sets
image data