Abstract
In many applications, there is a need to blindly separate independent sources from their linear instantaneous mixtures while the mixing matrix or source properties are slowly or abruptly changing in time. The easiest way to separate the data is to consider off-line estimation of the model parameters repeatedly in time shifting window. Another popular method is the stochastic natural gradient algorithm, which relies on non-Gaussianity of the separated signals and is adaptive by its nature. In this paper, we propose an adaptive version of two blind source separation algorithms which exploit non-stationarity of the original signals. The results indicate that the proposed algorithms slightly outperform the natural gradient in the trade-off between the algorithm’s ability to quickly adapt to changes in the mixing matrix and the variance of the estimate when the mixing is stationary.
This work was supported by California Community Foundation through Project No. DA-15-114599 and by the Czech Science Foundation through Project No. 17-00902S.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Jutten, C., Herault, J.: Blind separation of sources, Part I: an adaptive algorithm based on neuromimetic architecture. Signal Process. 24, 1–10 (1991)
Macchi, O., Moreau, E.: Self-adaptive source separation, Part I: convergence analysis of a direct linear network controled by the Herault-Jutten algorithm. IEEE Trans. Signal Process. 45, 918–926 (1997)
Moreau, E., Macchi, O.: High order contrasts for self-adaptive source separation. Int. J. Adapt. Control Signal Process. 10, 19–46 (1996)
Amari, S.I., Cichocki, A., Yang, H.H.: A new learning algorithm for blind signal separation. Adv. Neural Inf. Process. Syst. 8, 752–763 (1996)
Makino, S., Lee, T.W., Sawada, H.: Blind Speech Separation. Springer, Dordrecht (2007)
Tichavský, P., Yeredor, A.: Fast approximate joint diagonalization incorporating weight matrices. IEEE Trans. Signal Process. 57, 878–891 (2009)
Tichavský, P., Yeredor, A., Koldovský, Z.: A fast asymptotically efficient algorithm for blind separation of a linear mixture of block-wise stationary autoregressive processes. In: ICASSP 2009, Taipei, pp. 3133–3136 (2009)
Chabriel, G., Kleinsteuber, M., Moreau, E., Shen, H., Tichavský, P., Yeredor, A.: Joint matrices decompositions and blind source separation. IEEE Signal Process. Mag. 31, 34–43 (2014)
Koldovský, Z., Tichavský, P., Oja, E.: Efficient variant of algorithm fastICA for independent component analysis attaining the Cramér-Rao lower bound. IEEE Trans. Neural Netw. 17, 1265–1277 (2006)
Comon, P., Jutten, C.: Handbook of Blind Source Separation, Independent Component Analysis and Applications. Academic Press/Elsevier, Amsterdam (2010)
Hyvärinen, A., Karhunen, J., Oja, E.: Independent Component Analysis. Wiley-Interscience, New York (2001)
Tichavský, P., Koldovský, Z.: Fast and accurate methods of independent component analysis: a survey. Kybernetika 47, 426–438 (2011)
Koldovský, Z., Tichavský, P.: A comparison of independent component and independent subspace analysis algorithms. In: Proceedings of the European Signal Processing Conference (EUSIPCO), Glasgow, pp. 1447–1451 (2009)
Cardoso, J.-F., Pham, D.T.: Separation of non stationary sources. Algorithms and performance. In: Roberts, S.J., Everson, R.M. (eds.) Independent Components Analysis: Principles and Practice, pp. 158–180. Cambridge University Press, Cambridge (2001)
Tichavský, P., Koldovský, Z., Oja, E.: Performance analysis of the fastICA algorithm and Cramér-Rao bounds for linear independent component analysis. IEEE Trans. Signal Process. 54, 1189–1203 (2006)
Doron, E., Yeredor, A., Tichavský, P.: Cramér-Rao-induced bound for blind separation of stationary parametric Gaussian sources. IEEE Signal Process. Lett. 14, 417–420 (2007)
Tichavský, P., Koldovský, Z.: Weight adjusted tensor method for blind separation of underdetermined mixtures of nonstationary sources. IEEE Trans. Signal Process. 59, 1037–1047 (2011)
Tichavský, P., Šembera, O., Koldovský, Z.: Blind separation of mixtures of piecewise AR(1) processes and model mismatch. In: Vincent, E., Yeredor, A., Koldovský, Z., Tichavský, P. (eds.) LVA/ICA 2015. LNCS, vol. 9237, pp. 304–311. Springer, Heidelberg (2015). doi:10.1007/978-3-319-22482-4_35
Málek, J., Koldovský, Z., Tichavský, P.: Adaptive time-domain blind separation of speech signals. In: Vigneron, V., Zarzoso, V., Moreau, E., Gribonval, R., Vincent, E. (eds.) LVA/ICA 2010. LNCS, vol. 6365, pp. 9–16. Springer, Heidelberg (2010). doi:10.1007/978-3-642-15995-4_2
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Šembera, O., Tichavský, P., Koldovský, Z. (2017). Adaptive Blind Separation of Instantaneous Linear Mixtures of Independent Sources. In: Tichavský, P., Babaie-Zadeh, M., Michel, O., Thirion-Moreau, N. (eds) Latent Variable Analysis and Signal Separation. LVA/ICA 2017. Lecture Notes in Computer Science(), vol 10169. Springer, Cham. https://doi.org/10.1007/978-3-319-53547-0_17
Download citation
DOI: https://doi.org/10.1007/978-3-319-53547-0_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-53546-3
Online ISBN: 978-3-319-53547-0
eBook Packages: Computer ScienceComputer Science (R0)