Exploring sensitivity of joint diagonalization in convolutive blind source separation

This paper investigates several factors affecting the sensitivity of joint approximate diagonalization of a set of time varying cross-spectral matrices for blind separation of convolutive mixtures of speech signals. We study the effect of number of matrices in this set, and show that estimation of demixing system parameters is related to both several statistics of the perturbation term, occurring due to nonvanishing cross-spectra, and uniqueness of the joint diagonalizer measured by modulus of uniqueness parameter. Moreover, the effects of the number of multiple windows, to be used in cross-spectrum estimation, on the separation performance are examined via numerical simulations.