BLIND SPEECH SEPARATION IN A MEETING SITUATION WITH MAXIMUM SNR BEAMFORMERS

We propose a speech separation method for a meeting situation, where each speaker sometimes speaks and the number of speakers changes every moment. Many source separation methods have al-ready been proposed, however, they consider a case where all the speakers keep speaking: this is not always true in a real meeting. In such cases, in addition to separation, speech detection and the classification of the detected speech according to speaker become important issues. For that purpose, we propose a method that em-ploys a maximum signal-to-noise (MaxSNR) beamformer combined with a voice activity detector and online clustering. We also discuss the scaling ambiguity problem as regards the MaxSNR beamformer, and provide their solutions. We report some encouraging results for a real meeting in a room with a reverberation time of about 350 ms. Index Terms — Speech separation, maximum SNR beamformer, scaling ambiguity, voice activity detector, online clustering. 1