Blind deconvolution of signals using a complex recurrent network

An algorithm for the separation of mixtures of signals was derived by Jutten and Herault (1991) under the assumption that the signals are independent. This algorithm is based on higher order moments and has also been applied to deconvolving signal mixtures. In practical problems where the order of the convolving filter may be high, frequency domain approaches are known to provide a more computationally efficient method of deconvolution. In this paper, the authors introduce a complex recurrent network structure for performing blind deconvolution. The aim is to investigate the performance of this approach for separating unknown, convolved signals which may occur in a situation such as the well-known `cocktail-party problem´