Applications of deep learning in supervised speech separation

Recently, deep learning has been proposed and verified to possess the strong ability to learn and express complex features, which has brought significant research achievements in signal processing. As a challenging task in speech signal processing, monaural speech separation has always been the research focus of researchers. From the usage of traditional signal processing methods and shallow models to the applications of deep learning, a breakthrough has been made in the study of monaural speech separation. This paper firstly makes a brief introduction to various monaural speech separation methods, and then intensively presents the general process of speech separation and the applications of deep learning in speech separation.