Optimizing coherent demodulation for improved separation of overlapping sources

The complex modulators of coherent demodulation make the algorithm a natural fit for source separation, but the overlapping bands typically found in real audio mixtures present interference problems for the algorithm. This paper proposes reframing coherent demodulation as an optimization problem that distributes the energy in overlapping bands according to an optimally low-frequency strategy. The extension is shown to improve separation for sinewave mixtures and for mixtures of speech and music.