Using Counter-propagation Neural Network for Digital Audio Watermarking

Abstract

Recently, the watermarking is an important technique to protect copyright, which allows authentic watermark to be hidden in multimedia such as digital image, video and audio. Watermarking has been developed to protect digital media illegal reproductions and modifications. Traditionally, watermarking require complex procedures to embed and to extract watermark, such as randomizing the watermark, choose positions to embed and extract the watermark, embed the randomized watermark into the original audio and extracted the watermark from the specific positions. Therefore, in this paper, we propose a scheme called Counter-propagation Neural Network (CNN) for digital audio watermarking. Different from the traditional methods, the watermark is embedded in the synapses of CNN instead of the original audio signal. The experimental results show that the proposed method has capabilities of robustness, imperceptibility and authenticity.