A Neural Minor Component Analysis Approach to Robust Constrained Beamforming

Since the pioneering work of Amari and Oja, principal component neural networks and their extensions have become an active adaptive signal processing research eld. One of such extensions is minor component analysis (MCA), that proves to be e ective in problems such as robust curve/surface tting and noise reduction. The aims of this paper are to give a detailed and homogeneous review of one-unit rst minor/principal component analysis and to propose an application to robust constrained beamforming. In particular, after a careful presentation of rst/minor component analysis algorithms based on a single adaptive neuron, along with relevant convergence/steady-state theorems, it is shown how the adaptive robust constrained beamforming constrained theory by Cox et al. may be advantageously recast into an MCA seeting. Experimental results performed on a triangular array of microphones introduced in a teleconference context helps assessing the usefulness of the proposed theory.