Title :
Multichannel signal modeling and separation
Author :
Shamsunder, Sanyogita ; Giannakis, Georgios B.
Author_Institution :
Dept. of Electr. Eng., Colorado State Univ., Fort Collins, CO, USA
Abstract :
Separation of multiple signals from their superposition recorded at several sensors is addressed. The methods employ polyspectra of the sensor data in order to extract the unknown signals and estimate the exact coupling systems via a linear equation based method. Proposed schemes are also useful for multichannel blind deconvolution even when the input signals are colored with (possibly) overlapping spectra. Simulation results corroborate the applicability of the algorithm
Keywords :
deconvolution; parameter estimation; signal reconstruction; spectral analysis; algorithm; blind deconvolution; coupling systems; linear equation based method; multichannel signal modeling; multiple signals; polyspectra; sensor data; separation; superposition; Biomedical signal processing; Biosensors; Equations; Gas detectors; Interference; Linear systems; Microphones; Sensor systems; Signal processing algorithms; Source separation;
Conference_Titel :
Digital Signal Processing Workshop, 1994., 1994 Sixth IEEE
Conference_Location :
Yosemite National Park, CA
Print_ISBN :
0-7803-1948-6
DOI :
10.1109/DSP.1994.379847
