Time-scale invariant audio watermarking based on the statistical features in time domain

In audio watermarking, the robustness to desynchronization attacks such as TSM (Time-Scale Modification) operations, is still an open issue. In this paper, both mathematical proof and experimental testing show that the histogram shape (represented as the relative relation in the number of samples among three different histogram bins) and the audio mean are two robust features to the TSM attacks. Accordingly, a multi-bit robust audio watermarking algorithm based on the two statistical features is proposed by modifying the histogram. The audio histogram with equal-sized bins is extracted from a selected amplitude range referred to the audio mean, and then the relative relations in the number of samples among groups of three neighboring bins are designed to carry the watermark by reassigning the number of samples in the bins. The watermarked audio signal is perceptibly similar to the original one. Simulation results demonstrated that the hidden message is very robust to the TSM, cropping, and a variety of other distortions in Stirmark Benchmark for Audio.