Spread spectrum audio watermarking using frequency hopping and attack characterization

In this paper, we present a novel audio watermarking scheme that uses attack characterization to obtain high robustness against standard watermark attacks. The watermark embedding and detection are based on the frequency hopping method in the spectral domain. Perceptual transparency of the algorithm, achieved using frequency masking property of the human auditory system, was confirmed throughout listening tests. Detection robustness of the proposed scheme with and without attack characterization module was compared to standard direct sequence approach. Tests showed that the proposed method obtains higher robustness to standard watermarking attacks and that the attack characterization module significantly improves the performance of both algorithms. (C) 2003 Elsevier B.V. All rights reserved.