Subband Based Blind Source Separation with Appropriate Processing for Each Frequency Band

We propose subband-based blind source separation (BSS) for convolutive mixtures of speech. This is motivated by the drawback of frequency-domain BSS, i.e., when a long frame with a xed frame-shift is used for a few seconds of speech, the number of samples in each frequency bin decreases and the separation performance is degraded. In our proposed subband BSS, (1) by using a moderate number of subbands, a sufcien t number of samples can be held in each subband, and (2) by using FIR lters in each subband, we can handle long reverberation. Subband BSS achieves better performance than frequency-domain BSS. Moreover, subband BSS allows us to select the separation method suited to each subband. Using this advantage, we propose ecien t separation procedures that take the frequency characteristics of room reverberation and speech signals into consideration, (3) by using longer unmixing lters in low frequency bands, and (4) by adopting overlap-blockshift in BSS’s batch adaptation in low frequency bands. Consequently, subband processing appropriate for each frequency bin is successfully realized with the proposed subband BSS.