出版社：Faculty of Humanities, Kaunas University of Technology
其他摘要：Audio watermarking is a process to hide digital data without being seen or heard by the sense of sight or hearing. Watermaking is applied to insert the copyright on digital media, such as an image file, an audio file or a video file. In this paper, we propose watermarking procedure to embed spread spectrum watermark into frequency domain of adaptive selected subband from host audio. Lifting Wavelet Transform (LWT) is used to decompose the host audio into several subbands, and then Fast Fourier Transform (FFT) transforms selected several subbands with lowest energy. The watermark image is converted into one-dimensional signal, then it is modulated by imperceptible pseudo-noise (PN) code with controlled gain. Next, the frequency domain of audio is added by modulated and imperceptible watermark prior to transforming it to time domain by Inverse FFT (IFFT) obtaining watermarked subbands. Finally, the watermarked subbands are combined with other unused subbands by inverse LWT (ILWT) becoming the perfect version of watermarked audio. The result of this method has good robustness against most attacks from stirmark benchmark experiments, good imperceptibility with Signal to Noise Ratio (SNR) more than 30 dB and payload 172.66 bps.
