Konferenční příspěvek

Koldovský Z., Tichavský P.

2008 Hands-free Speech Communication and Microphone Arrays

IEEE

Trento

2008

978-1-4244-2338-5

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

blind source separation, audio signals

We present a novel time-domain method for blind separation of convolutive mixture of audio sources (the cocktail party problem). The method allows efficient separation with good signal-to-interference ratio (SIR) and signal-to-distortion ratio (SDR) using short data segments only. In practice, we are able to separate 2-4 speakers from audio recording of the length less than 6000 samples, which is less than 1-s in the 8-kHz sampling. The average time needed to process the data with filter of the length 20 was 2.2 seconds in Matlab v.-7.2 on an ordinary PC with 3GHz processor.