STATISTICAL PROPERTIES OF STFT RATIOS FOR TWO CHANNEL SYSTEMS AND APPLICATIONS TO BLIND SOURCE SEPARATION

Radu Balan and Justinian Rosca, Siemens Corporate Research
frvbalan,roscag@scr.siemens.com

The ratio of the short time Fourier transform (STFT) coefficients of signals received at two sensors can factor out the role of the power spectrum of emitting sources, under an assumption called disjoint orthogonality. Thus, it can reveal parameters specific to the mixing scenario and serve as a basis for channel estimation techniques. In this paper we analyze and extend a source separation method based on the use of STFT ratios of two sensor in­ puts, called DUET. We generalize the problem formulation in DUET, and prove that considerably weaker assumptions about the classes of input signals are sufficient to apply the derived techniques. The analysis centers on the notion of ratio­estimator and a novel stochastic model that enabled us to derive the maximum likelihood ratio­estimator. Derived techniques can be effectively applied to source separation, source localization, signal enhancement, and noise reduction when using a twin microphone system, both in echoic environments and degenerate situations.