Skip to Main Content
Digital audio watermarking is embedded inaudible information into digital audio data for the purposes of copyright protection, ownership verification, covert communication, and/or auxiliary data carrying. In this paper, a new digital audio watermarking algorithm is proposed, which based on Neural Networks and in the Wavelet Domain and corresponding algorithms of watermark generation, embedding, and extraction. When compared with other traditional algorithms, the scheme has the advantage of extracting watermark without the participation of origin audio signal, and low computing amount. Moreover, from the experimental result, we can see that the wave shape of original audio signal is not notable different to the watermark embedded one, so it won't influence the audio effect. Meanwhile, watermark is clear and visible after the various attacks; this result shows that the algorithm has the advantage of high robustness.