Pseudoanechoic blind source separation with improved Wiener postfilter
Leandro Ezequiel Di Persia, Diego Humberto Milone, Masuzo Yanagida · 2009
The pseudoanechoic model was proposed recently to simplify the parameter estimation in blind source separation based on frequency-domain independent component analysis. In the method, after separation based in the pseudoanechoic model a time-frequency Wiener postfilter to improve the separation is applied. In this contribution, a deeper analysis of the working principles of the Wiener post- filter is presented. Furthermore, a variation of this postfilter to improve the performance using the information of previous frames is in- troduced. The improvements obtained through the new method are evaluated in an automatic speech recognition task and with the PESQ ob- jective quality measure. The results show an increased robustness and stability of the pro- posed method.