点击次数：

论文类型：会议论文

发表时间：2004-06-27

收录刊物：EI、CPCI-S、Scopus

卷号：2

页面范围：1013-1017

关键字：blind source separation; independent component analysis; speech encryption

摘要：In this paper, we present a novel speech encryption algorithm based on blind source separation (BSS). Our approach integrates a modified time domain scrambling scheme with an amplitude scrambling method which masks the speech signal with a random noise by specific mixing. The resulting system can securely encrypt the speech files for the purpose of storing speech messages and transmitting them over the Internet. There are two major advantages associated with this system. The first advantage is that it makes the encrypted speech sound like white noise. The second advantage is that it does not impose any restriction on the key space. Our system is systematically evaluated, and it shows a high level of security with excellent audio quality.