Two-microphone Separation of Speech Mixtures

Michael Syskind Pedersen, DeLiang Wang, Jan Larsen, Ulrik Kjems

AbstractIn this demonstration we show the separation of 3-7 mixed speech sources based on information from two microphones. Separation with background noise is demonstrated too.

The algorithms are described in

1] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: "Two-microphone Separation of Speech Mixtures," 2006, submited for journal publication.

See also,

[2] Michael Syskind Pedersen, DeLiang Wang, Jan Larsen and Ulrik Kjems: "Overcomplete Blind Source Separation by Combining ICA and Binary Time-Frequency Masking," in proceedings of IEEE International workshop on Machine Learning for Signal Processing, pp. 15-20, 2005.
KeywordsDemo, Underdetermined ICA
TypeDemo
Year2006    Month January
NoteMatlab source code available at: http://www.imm.dtu.dk/pubdb/p.php?4399
Electronic version(s)[pdf] [zip]
BibTeX data [bibtex]
IMM Group(s)Intelligent Signal Processing