Research On Blind Signal Processing In Communication Field

Since the original works by Hérault, et al, great advances have been made in the area of blind source separation(BSS). It has become a hotspot of modern signal processing. It has many protential applications in communication, speech processing, image processing, biomedicine and radar technology, and it even finds applications in financial data analysis. However, there are still many open issues that need further investigation. Some new approaches are presented based on the contributions by former researchers.Generally, on one hand, BSS approaches can be classified into two groups according to the mixing channels: approaches for instantaneous mixtures and that for convolutive mixtures. On the other hand, it can be categorized into three classes with respect to statistical information exploited: second-order statistics (SOS), high-order statistics (HOS) and parameters defined in information theory. In addition, BSS approaches can also be time-domain approaches and frequency-domain approaches according to their implementation manner. BSS theory and approaches are studied along these three lines in this dissertation. Analysed instantaneous mixtures and that of convolutive mixtures modals as well as the separative modal, bring out the disciplines of an separative modal which can be create. There for, as second-order statistics algorithm made use of the non-stationarity of signals, high-order statistics method use non-Gaussianity to express, will information theory took K-L divergence as its object function. According to this information, this paper have put forward some basic method of separation. Summarized the classical method of ICA, combined with further research. On the research of convolutive mixtures, deal them with algorithm either in time-domain or frequence-domain.