Fig. 14From: Localization based stereo speech source separation using probabilistic time-frequency masking and deep neural networksSDR to unseen rooms, in underdetermined case. We select each of the four rooms to generate the training dataset and use the BRIRs from the four rooms (one by one respectively) to generate the test dataset. The interferer is varied from −90° to +90° with the step of 5°Back to article page