Source separation for reverberant environment

A system comprising:

• one or more processors;
• and
• a non-transitory computer-readable medium storing instructions that, upon execution by the one or more processors, cause the one or more processors to perform operations of source separation, the operations comprising:
• capturing first microphone signals for each individual one of at least one source respectively by at least two microphones for a period during which only the individual one produces sound;
• learning mixing parameters for modeling acoustic paths between the at least one source and the at least two microphones based on the first microphone signals and a spectral basis of the at least one source via a non-negative matrix factorization method by considering a power spectrogram of the first microphone signals of each source as a power spectrogram of the source;
• capturing second microphone signals respectively by the at least two microphones for a period during which all of the at least one source produce sounds;
• estimating a reconstruction model based on the mixing parameters, the spectral basis and the second microphone signals, wherein the reconstruction model is adapted to reconstruct spatial images of the at least one source on the microphones, and wherein the mixing parameters for each of the at least one source are characterized as ratios between spatial images of the source on the microphones and the spatial image of the source on a reference one of the microphones;
• and
• performing the source separation by applying the reconstruction model.