ISCA Archive Interspeech 2007
ISCA Archive Interspeech 2007

Time-domain blind audio source separation using advanced ICA methods

Zbyněk Koldovský, Petr Tichavský

In this paper, a prototype of novel algorithm for blind separation of convolutive mixtures of audio sources is proposed. The method works in time-domain, and it is based on the recently very successful algorithm EFICA for Independent Component Analysis, which is an enhanced version of more famous FastICA. Performance of the new algorithm is very promising, at least, comparable to other (mostly frequency domain) algorithms. Audio separation examples are included.


doi: 10.21437/Interspeech.2007-314

Cite as: Koldovský, Z., Tichavský, P. (2007) Time-domain blind audio source separation using advanced ICA methods. Proc. Interspeech 2007, 846-849, doi: 10.21437/Interspeech.2007-314

@inproceedings{koldovsky07_interspeech,
  author={Zbyněk Koldovský and Petr Tichavský},
  title={{Time-domain blind audio source separation using advanced ICA methods}},
  year=2007,
  booktitle={Proc. Interspeech 2007},
  pages={846--849},
  doi={10.21437/Interspeech.2007-314}
}