It is possible to blindly separate an arbitrary number of sources given just two anechoic mixtures provided the time-frequency representations of the sources do not overlap, a condition which we call W-disjoint orthogonality. We define a power weighted two-dimensional histogram constructed from the ratio of the time-frequency representations of the mixtures which is shown to have one peak for each source with: peak location corresponding to the relative amplitude and delay mixing parameters. All of the time-frequency points which yield estimates in a given peak are exactly all the non-zero magnitude components of one of the sources. We introduce the concept of approximate W-disjoint orthogonality, present experimental results demonstrating the level of approximate W-disjoint orthogonality of speech in mixtures of various order, and show that even with imperfect W-disjoint orthogonality the histogram can be used to determine the mixing parameters and separate sources. Example demixing results can be found online: http://www.princeton.edu/∼srickard/bss.html
[1]
M. Hulle.
Clustering approach to square and non-square blind source separation
,
1999
.
[2]
Özgür Yilmaz,et al.
Blind separation of disjoint orthogonal signals: demixing N sources from 2 mixtures
,
2000,
2000 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.00CH37100).
[3]
Scott Rickard,et al.
The In uence of Windowing on Time Delay Estimates
,
2001
.
[4]
I. Daubechies.
Ten Lectures on Wavelets
,
1992
.
[5]
Terrence J. Sejnowski,et al.
Blind source separation of more sources than mixtures using overcomplete representations
,
1999,
IEEE Signal Processing Letters.
[6]
Justinian P. Rosca,et al.
REAL-TIME TIME-FREQUENCY BASED BLIND SOURCE SEPARATION
,
2001
.