With the cross-fertilization of applications and the ever-increasing sca...
Spatial architecture is a high-performance architecture that uses contro...
Diffusion Probability Models (DPMs) have made impressive advancements in...
Deep learning applications are being transferred from the cloud to edge ...
Due to user privacy and regulatory restrictions, federate learning (FL) ...
Time Delay Neural Networks (TDNN)-based methods are widely used in diale...
Attention-based models have made tremendous progress on end-to-end autom...
This paper describes the systems submitted by the department of electron...
Despite the recent successes of deep neural networks, it remains challen...