Ensemble EMD Based Data Hiding Technique in an Audio Signal

Abstract

In this paper we proposed a novel data hiding algorithm based on Ensemble empirical mode decomposition (EEMD) is used to decompose the watermark signal and combined with the decomposed data is introduced. The audio signal is decomposed by Ensemble Empirical Mode Decomposition (EEMD) into intrinsic oscillatory components called Intrinsic Mode Functions (IMFs). This approach having a sifting an ensemble of added-white noise signal and considered the mean. A uniform reference frame in the time-frequency space provides the effect of white noise; therefore, the portion of the signal of comparable scale in one IMF is collated by the added noise. The secret data is embedded in the last IMF of the signal, which is a low frequency mode, will be stable under different attacks. Finally, the exactness of the EEMD method for decomposition and extraction verified with the simulation results.
Keywords: Empirical Mode Decomposition (EMD); Ensemble Empirical Mode Decompositions (EEMD); Intrinsic Mode Function (IMF);