Identification of speech source coupling between sensors in reverberant noisy environments

An important component of a multichannel hands-free communication system is the identification of the coupling between sensors in response to a desired speech signal. In this letter, a system identification approach adapted to speech signals is proposed. A weighted least-squares optimization criterion is introduced, which incorporates an indicator function for the presence of the desired signal in the observed signals. We show that compared to a competing nonstationarity-based method, a significantly smaller error variance is achievable.