Abstract
Estimating audio and musical signals from single channel mixtures often, if not always, involves a transformation of the mixture signal to the time-frequency (T-F) domain in which a masking operation takes place. Masking is realized as an element-wise multiplication of the mixture signal's T-F representation with a ratio of computed sources' spectrogram. Studies have shown that the performance of the overall source estimation scheme is subject to the sparsity and disjointness properties of a given T-F representation. In this work we investigate the potential of an optimized pseudo quadrature mirror filter-bank (PQMF), as a T-F representation for music source separation tasks. Experimental results, suggest that the PQMF maintains the aforementioned desirable properties and can be regarded as an alternative for representing mixtures of musical signals.