Sparse Blind Source Deconvolution with Application to High Resolution Frequency Analysis
The title of the paper refers to an extension of the classical blind source separation where the mixing of unknown sources is assumed in the form of convolution with impulse response of unknown linear dynamics. A further key assumption of our approach is that source signals are considered to be sparse with respect to a known dictionary, which suggests a mixed L 1/L 2-optimization as a possible formalism for solving the un-mixing problem. We demonstrate the effectiveness of the framework numerically.
KeywordsImpulse Response Sparse Representation Blind Source Separation Toeplitz Matrice Gradient Projection Method
- 2.Bruckstein, A.M., Donoho, D.L., Elad, M.: From sparse solutions of systems of equations to sparse modeling of signals and images. SIAM Review (2008)Google Scholar
- 6.Candes, E., Braun, N., Wakin, M.: Sparse signal and image recovery from compressive samples. In: 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, pp. 976–979 (2007)Google Scholar
- 18.Malioutov, D.M., Cetin, M., Willsky, A.S.: Optimal sparse representations in general overcomplete base. In: IEEE International Conference on Acoustics, Speech, and Signal Processing (2004)Google Scholar
- 21.Romberg, J.K.: Sparse signal recovery via ℓ1 minimization. In: Proceedings of the 40th Annual Conference on Information Sciences and Systems, March 2006, pp. 213–215 (2006)Google Scholar