EURASIP Journal on Audio, Speech, and Music Processing
Volume 2009 (2009), Article ID 130567, 10 pages
doi:10.1155/2009/130567
Research Article

Musical Sound Separation Based on Binary Time-Frequency Masking

Yipeng Li1 and DeLiang Wang2

1Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210-1277, USA
2Department of Computer Science and Engineering and Center of Cognitive Science, The Ohio State University, Columbus, OH 43210-1277, USA

Received 15 November 2008; Revised 20 March 2009; Accepted 16 April 2009

Academic Editor: Q.-J. Fu

Copyright © 2009 Yipeng Li and DeLiang Wang. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

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 time-frequency 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.