Copyright-proving scheme for audio with counter-propagation neural networks

Protecting the intellectual property rights (IPR) of digital media has become an important issue. In this paper, counter-propagation neural networks (CPN) are applied to audio copyright protection. The db4 filter of the Daubechies wavelet is used on the original audio signals. The coefficients obtained from the 4-level Daubechies (db4) filter and the corresponding copyright information are used to train the CPN. Since the low-frequency components of DWT are robust, most noise is excluded. The CPN has memory and fault tolerance, so most attacks do not degrade the quality of the extracted copyright image. Moreover, the copyright generation procedure and the verification procedure are integrated into the proposed CPN method. Experimental results show that the proposed CPN-based method is robust, inaudible, and authentic.