Musical Sound Separation Based on Binary Time-Frequency Masking

The problem of overlapping harmonics is particularly acute in musical sound separation and has not been addressed adequately. We propose a monaural system based on binary time-frequency masking with an emphasis on robust decisions in timefrequency regions, where harmonics from different sources overlap. Our computational auditory scene analysis system exploits the observation that sounds from the same source tend to have similar spectral envelopes. Quantitative results show that utilizing spectral similarity helps binary decision making in overlapped time-frequency regions and significantly improves separation performance.