Advertisement

A New Link Between Joint Blind Source Separation Using Second Order Statistics and the Canonical Polyadic Decomposition

  • Dana LahatEmail author
  • Christian Jutten
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10891)

Abstract

In this paper, we discuss the joint blind source separation (JBSS) of real-valued Gaussian stationary sources with uncorrelated samples from a new perspective. We show that the second-order statistics of the observations can be reformulated as a coupled decomposition of several tensors. The canonical polyadic decomposition (CPD) of each such tensor, if unique, results in the identification of one or two mixing matrices. The proposed new formulation implies that standard algorithms for joint diagonalization and CPD may be used to estimate the mixing matrices, although only in a sub-optimal manner. We discuss the uniqueness and identifiability of this new approach. We demonstrate how the proposed approach can bring new insights on the uniqueness of JBSS in the presence of underdetermined mixtures.

Keywords

Joint blind source separation Independent vector analysis Tensor Canonical polyadic decomposition Uniqueness Identifiability 

References

  1. 1.
    Kim, T., Eltoft, T., Lee, T.-W.: Independent vector analysis: an extension of ICA to multivariate components. In: Rosca, J., Erdogmus, D., Príncipe, J.C., Haykin, S. (eds.) ICA 2006. LNCS, vol. 3889, pp. 165–172. Springer, Heidelberg (2006).  https://doi.org/10.1007/11679363_21CrossRefzbMATHGoogle Scholar
  2. 2.
    Li, Y.O., Adalı, T., Wang, W., Calhoun, V.D.: Joint blind source separation by multiset canonical correlation analysis. IEEE Trans. Signal Process. 57(10), 3918–3929 (2009)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Hitchcock, F.L.: The expression of a tensor or a polyadic as a sum of products. J. Math. Phys. 6(1), 164–189 (1927)CrossRefGoogle Scholar
  4. 4.
    Li, X.L., Adalı, T., Anderson, M.: Joint blind source separation by generalized joint diagonalization of cumulant matrices. Signal Process. 91(10), 2314–2322 (2011)CrossRefGoogle Scholar
  5. 5.
    Congedo, M., Phlypo, R., Chatel-Goldman, J.: Orthogonal and non-orthogonal joint blind source separation in the least-squares sense. In: Proceedings of the EUSIPCO, Bucharest, pp. 1885–1889, August 2012Google Scholar
  6. 6.
    Lahat, D., Jutten, C.: Joint analysis of multiple datasets by cross-cumulant tensor (block) diagonalization. In: Proceedings of the SAM, Rio de Janeiro, July 2016Google Scholar
  7. 7.
    Lahat, D., Jutten, C.: Joint independent subspace analysis using second-order statistics. IEEE Trans. Signal Process. 64(18), 4891–4904 (2016)MathSciNetCrossRefGoogle Scholar
  8. 8.
    Kruskal, J.B.: Three-way arrays: rank and uniqueness of trilinear decompositions, with application to arithmetic complexity and statistics. Proc. London Math. Soc. 18(2), 95–138 (1977)MathSciNetzbMATHGoogle Scholar
  9. 9.
    Lahat, D., Adalı, T., Jutten, C.: Multimodal data fusion: an overview of methods, challenges and prospects. Proc. IEEE 103(9), 1449–1477 (2015)CrossRefGoogle Scholar
  10. 10.
    Anderson, T.W.: An introduction to multivariate statistical analysis. Wiley, New York (1958)zbMATHGoogle Scholar
  11. 11.
    Vía, J., Anderson, M., Li, X.L., Adalı, T.: A maximum likelihood approach for independent vector analysis of Gaussian data sets. In: Proceedings of the MLSP, Beijing, September 2011Google Scholar
  12. 12.
    Vía, J., Anderson, M., Li, X.L., Adalı, T.: Joint blind source separation from second-order statistics: Necessary and sufficient identifiability conditions. In: Proceedings of the ICASSP, Prague, pp. 2520–2523, May 2011Google Scholar
  13. 13.
    Anderson, M., Fu, G.S., Phlypo, R., Adalı, T.: Independent vector analysis: identification conditions and performance bounds. IEEE Trans. Signal Process. 62(17), 4399–4410 (2014)MathSciNetCrossRefGoogle Scholar
  14. 14.
    Lahat, D., Jutten, C.: An alternative proof for the identifiability of independent vector analysis using second order statistics. In: Proceedings of the ICASSP, Shanghai, March 2016Google Scholar
  15. 15.
    Gong, X.F., Lin, Q.H., Cong, F.Y., De Lathauwer, L.: Double coupled canonical polyadic decomposition for joint blind source separation (2017). arXiv:1612.09466 [stat.ML]

Copyright information

© Springer International Publishing AG, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-labGrenobleFrance

Personalised recommendations