In this paper, we propose analytical formulas that involve second-order statistics for separating two signals. The method utilizes source decorrelation and correlation function diversity. In particular, the proposed SOBAS (Second-Order Blind Analytical Separation) algorithm differs from the ASOBI (Analytical Second-Order Blind Identification) algorithm in that it does not require prior knowledge or estimation of the noise variance. Computer simulations demonstrate the effectiveness of the proposed method.