A fast fixed-point algorithm for independent component analysis
Neural Computation
Digital audio watermarking in the cepstrum domain
IEEE Transactions on Consumer Electronics
A novel echo-hiding scheme with backward and forward kernels
IEEE Transactions on Circuits and Systems for Video Technology
A blind source separation based multi-bit digital audio watermarking scheme
ISNN'06 Proceedings of the Third international conference on Advances in Neural Networks - Volume Part III
Hi-index | 0.00 |
An effective digital audio watermarking scheme based on blind source separation (BSS) for blind watermark detection is proposed in this paper. In the embedding procedure, the original watermark is modulated by chaotic sequence to generate an embedding watermark. Then watermarked audio signal is combined by two signals which are mixed by original audio signal and embedding watermark according to BSS mixing model. In the detecting procedure, watermarked audio signal is split into two signals first, and then BSS technique is applied to them to obtain the separated embedding watermark. At last, we can determine the watermark presence by correlation values between the separated embedding watermark and embedding watermark. Experimental results show the effectiveness of the proposed method.