research
∙
02/20/2023
A DNN based Normalized Time-frequency Weighted Criterion for Robust Wideband DoA Estimation
Deep neural networks (DNNs) have greatly benefited direction of arrival ...
share
research
∙
11/16/2022
Leveraging Heteroscedastic Uncertainty in Learning Complex Spectral Mapping for Single-channel Speech Enhancement
Most speech enhancement (SE) models learn a point estimate, and do not m...
research
∙
10/13/2022
Improved Bounds on Neural Complexity for Representing Piecewise Linear Functions
A deep neural network using rectified linear units represents a continuo...
research
∙
11/17/2021
A Generalized Proportionate-Type Normalized Subband Adaptive Filter
We show that a new design criterion, i.e., the least squares on subband ...
research
∙
11/10/2021
ResNEsts and DenseNEsts: Block-based DNN Models with Improved Representation Guarantees
Models recently used in the literature proving residual networks (ResNet...
research
∙
10/31/2019
Team NCTU: Toward AI-Driving for Autonomous Surface Vehicles – From Duckietown to RobotX
Robotic software and hardware systems of autonomous surface vehicles hav...
research
∙
10/31/2019
Duckiefloat: a Collision-Tolerant Resource-Constrained Blimp for Long-Term Autonomy in Subterranean Environments
There are several challenges for search and rescue robots: mobility, per...
research
∙
10/26/2019