A deep learning based design for speech signal deepfake generation and detection

Abstract

Applications of deep learning to solve complex problems related to computer vision and human level control system has been successfully implemented in real life. On the other hand, deep leaning based systems can also cause harm to the privacy and security of the personnel or a system. One of the threats that is powered by deep learning and AI is deep fake technique which is used to create fake images, video and audios that are not identified by human visual or audio system. This makes it difficult for human to distinguish between the original data and the deep fake data. This paper aims at discussing the techniques or algorithm require to create deepfake and to detect the deepfake in audiodata.