Abstract: Deep learning has been widely applied to seismic data interpolation. However, most existing methods are based on supervised learning, suffering from limitations such as low generalization ...
Abstract: This paper proposes a novel meta-transfer learning method to improve automatic speech recognition (ASR) performance in low-resource languages. Nowadays, we are witnessing high interest in ...
Most teachers (myself included) don’t want to rely on lectures and worksheets to do our jobs. The problem is that it’s time-intensive and difficult to plan for lots and lots of active learning, which ...