A subspace method for the blind extraction of a cyclostationary source

The need for blindly separating mixtures of source signals arises in many signal processing applications. The solution to this problem was found using emerging blind source separation (BSS) techniques which rely on the knowledge of the number of independent sources present in the mixture. This paper deals with the case where the number of sources is unknown and statistical independence may not apply, but where there is only one signal of interest (SOI) to be separated. We propose a method for extracting this SOI by exploiting its cyclostationarity through a subspace decomposition of the observations. This method is first developed for instantaneous mixtures and is then extended to the convolutive case in the frequency domain where it does not suffer from the permutation problem as does classical BSS. Experiments on electrocardiogram and industrial data are finally performed and illustrate the high performance of the proposed method.