Web projektu DAR

Výzkumné centrum
Data - Algoritmy - Rozhodování

Založeno v roce 2005 s podporou MŠMT ČR (projekt 1M0572)

Publikace

Time-Domain Blind Audio Source Separation using Advanced ICA Methods

Typ:

Konferenční příspěvek

Autoři publikace:

Koldovský Z., Tichavský P.

Název sborniku:

Proccedings of the 8th Annual Conference of the International Speech Communication Association. Interspeech 2007

Nakladatel:

University Bonn

Místo vydání:

Bonn

Rok:

2007

Kontaktní osoba:

Ing. Petr Tichavský, CSc. (ÚTIA - Oddělení stochastické informatiky)

Klíčová slova:

independent component analysis, multichannel blind deconvolu

Anotace:

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.