Deep neural networks (DNNs) have greatly benefited direction of arrival ...
Most speech enhancement (SE) models learn a point estimate, and do not m...
A deep neural network using rectified linear units represents a continuo...
We show that a new design criterion, i.e., the least squares on subband
...
Models recently used in the literature proving residual networks (ResNet...
Robotic software and hardware systems of autonomous surface vehicles hav...
There are several challenges for search and rescue robots: mobility,
per...
Based on the direct perception paradigm of autonomous driving, we invest...