The present examples refer to methods, apparatus and techniques for obtaining a plurality of output signals associated with different sources (e.g. audio sources). In one example, it is possible to: combine a first input signal, or a processed version thereof, with a delayed and scaled version of a second input signal, to obtain a first output signal; and combine a second input signal, or a processed version thereof, with a delayed and scaled version of the first input signal, to obtain a second output signal. It is possible to determine, e.g. using a random direction optimization: scaling values, to obtain the delayed and scaled versions of the first and second input signals; and delay values, to obtain the delayed and scaled versions of the first and second input signals.