This document proposes a new blind source separation method that takes advantage of both independence and sparsity using an overcomplete Gabor representation. The method is shown to work for both under-determined and determined cases. It formulates source separation as an optimization problem that enforces decorrelation of the sources (a consequence of independence) along with sparse properties. An algorithm is presented that alternates between estimating the sources and mixing matrix. Experimental results demonstrate the method outperforms other approaches like DUET and FastICA in terms of metrics like SDR and SIR, and is more robust to noise.