2009 Articles
Source Separation Based on Binaural Cues and Source Model Constraints
We describe a system for separating multiple sources from a two-channel recording based on interaural cues and known characteristics of the source signals. We combine a probabilistic model of the observed interaural level and phase differences with a prior model of the source statistics and derive an EM algorithm for finding the maximum likelihood parameters of the joint model. The system is able to separate more sound sources than there are observed channels. In simulated reverberant mixtures of three speakers the proposed algorithm gives a signal-to-noise ratio improvement of 2.1 dB over a baseline algorithm using only interaural cues.
Subjects
Files
- WeissME08-MESSL-SP.pdf application/pdf 299 KB Download File
Also Published In
- Title
- 9th annual conference of the International Speech Communication Association 2008: (INTERSPEECH 2008) Brisbane, Australia, 22-26 September 2008
- Publisher
- International Speech Communication Association
More About This Work
- Academic Units
- Electrical Engineering
- Published Here
- June 27, 2012