Sign in
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:
CoRR (2022)
Keyphrases
</>
audio visual
loss function
deep learning
doa estimation
multi modal
pairwise
sound source
visual information
unsupervised learning
support vector
multimedia
machine learning
visual data
canonical correlation analysis
pattern recognition
image features
data sets
image segmentation
information retrieval