Blind sources separation based on bilinear time-frequency representations: A performance analysis
暂无分享,去创建一个
In this communication, the problem of blind sources separation is considered. Many solutions have been brought to that problem, among which the method recently introduced in [1][2], that consists in joint-diagonalizing a combined set of “spatial t-ƒ distributions (stƒd)” matrices. In [4], we have introduced new criteria of selection of the t-ƒ points to use in the building of matrices sets to joint-diagonalize or to anti joint-diagonalize. As these criteria are no more sufficient in the noisy case, new constraints are introduced in the shape of thresholds (calculated both by Bayesian and Neyman-Pearson approaches) leading to new criteria of selection of the matrices sets. Performance studies on these new algorithms are proposed versus SNR and computer simulations are provided.
[1] Nadège Thirion-Moreau,et al. BLIND SOURCES SEPARATION USING BILINEAR AND QUADRATIC TIME-FREQUENCY REPRESENTATIONS , 2001 .
[2] D. Declercq,et al. Statistical properties of the pseudo-Wigner-Ville representation of normal random processes , 1999, Signal Process..
[3] Moeness G. Amin,et al. Blind source separation based on time-frequency signal representations , 1998, IEEE Trans. Signal Process..
[4] Eric Moreau,et al. A generalization of joint-diagonalization criteria for source separation , 2001, IEEE Trans. Signal Process..