Institute of Information Theory and Automation

You are here

Bibliography

Conference Paper (international conference)

Time-Domain Blind Audio Source Separation using Advanced ICA Methods

Koldovský Z., Tichavský Petr

: Proccedings of the 8th Annual Conference of the International Speech Communication Association. Interspeech 2007, p. 1-4

: Interspeech 2007 /8./, (Antwerpen, BE, 27.08.2007-31.08.2007)

: CEZ:AV0Z10750506

: 1M0572, GA MŠk, GA102/05/0278, GA ČR, GP102/07/P384, GA ČR

: independent component analysis, multichannel blind deconvolution

(eng): 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.

(cze): V článku je navržen prototyp nového algoritmu pro slepou separaci konvolutorních směsí akustických signálů. Algoritmus pracuje v časové oblasti a je založen na úspěšném algoritmu EFICA pro analýzu nezávislých komponent. Navržený algorimus má velice slibné výsledky a je přinejmenším porovnatelný s dalšími metodami slepé separace akustických signálů.

: BI

2019-01-07 08:39