no code implementations • 13 Dec 2022 • Bokyeung Lee, Kyungdeuk Ko, Jonghwan Hong, Hanseok Ko
With these modules, then we employ reinforcement learning in search of an optimal image denoising network at a module level.
no code implementations • 20 Oct 2022 • Donghyeon Kim, Kyungdeuk Ko, David K. Han, Hanseok Ko
In order to train the network for more robust performance in noisy environments, we introduce the LOw Variant Orthogonal (LOVO) loss.
no code implementations • 23 Sep 2021 • Donghyeon Kim, Kyungdeuk Ko, Jeonggi Kwak, David K. Han, Hanseok Ko
Keyword Spotting (KWS) from speech signals is widely applied to perform fully hands-free speech recognition.