Music and vocal separation using multiband modulation based features

The potential use of non-linear speech features has not been investigated for music analysis although other commonly used speech features like Mel Frequency Ceptral Coefficients (MFCC) and pitch have been used extensively. In this paper, we assume an audio signal to be a sum of modulated sinusoidal and then use the energy separation algorithm to decompose the audio into amplitude and frequency modulation components using the non-linear Teager-Kaiser energy operator. We first identify the distribution of these non-linear features for music only and voice only segments in the audio signal in different Mel spaced frequency bands and show that they have the ability to discriminate voice and music from an audio signal. The proposed method is based on Kullback-Leibler divergence measure and is evaluated using a set of Indian classical songs from three different artists. Experimental results show that the discrimination ability is evident in certain low and mid frequency bands (100-1500 Hz).