Blind audio source separation based on a new system model and the Savitzky-Golay filter

Pengfei Xu – Yinjie Jia – Mingxin Jiang

   Blind source separation (BSS) is a research hotspot in the field of signal processing. This scheme is widely applied to separate a group of source signals from a given set of observations or mixed signals. In the present study, the Savitzky-Golay filter is applied to smooth the mixed signals, adopt a simplified cost function based on the signal to noise ratio (SNR) and obtain the demixing matrix accordingly. To this end, the generalized eigenvalue problem is solved without conventional iterative methods. It is founded that the proposed algorithm has a simple structure and can be easily implemented in diverse problems. The obtained results demonstrate the good performance of the proposed model for separating audio signals in cases with high signal to noise ratios.

Keywords: blind source separation, moving average, Savitzky-Golay smoothing, cost function, audio signal

[full-paper]