Semi-blind Source Separation Using Head-Related Transfer Functions

Michael Syskind Pedersen, Lars Kai Hansen, Ulrik Kjems, Karsten Bo Rasmussen

AbstractAn online blind source separation algorithm which is a special case
of the geometric algorithm by Parra and Fancourt has been implemented
for the purpose of separating sounds recorded at microphones
placed at each side of the head. By using the assumption
that the position of the two sounds are known, the source separation
algorithm has been geometrically constrained. Since the
separation takes place in a non free-field, a head-related transfer
function (HRTF) is used to simulate the response between microphones
placed at the two ears. The use of a HRTF instead of assuming
free-field improves the separation with approximately 1 dB
compared to when free-field is assumed. This indicates that the
permutation ambiguity is solved more accurate compared to when
free-field is assumed.
KeywordsConvolutive Blind Source Separation, HRTF
TypeConference paper [With referee]
ConferenceICASSP 2004
Year2004    Month May    Vol. V    pp. 713-716
Electronic version(s)[pdf] [ps]
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing