In this paper we perform an in depth study of how data augmentation techniques improve
synthetic or spoofed audio detection. Specifically, we propose methods to deal with channel …

语音承载着人类语言和说话人身份信息, 通过语音伪造技术可以精确模仿目标说话人的声音以
达到欺骗人或机器听觉的目的. 目前, 深度伪造(Deepfake) 正在对全球的政治经济及社会稳定带 …

Due to the open nature of voice and voice interface, an adversary can spoof voice
recognition systems by replaying pre-recorded voice commands from legitimate users …