Power-Weighted Divergences for Relative Attenuation and Delay Estimation

Power-weighted estimators have recently been proposed for relative attenuation and delay estimation in blind source separation. Their provenance lies in the observation that speech is approximately windowed-disjoint orthogonal (WDO) in the time-frequency (TF) domain; it has been reported that using WDO, derived from TF representations of speech, improves mixing parameter estimation. We show that power-weighted relative attenuation and delay estimators can be derived from a particular case of a weighted Bregman divergence. We then propose a wider class of estimators, which we tune to give better parameter estimates for speech.