Seda Senay



Nonstationary Blind Source Separation Using Slepian Spectral Estimator

pdf PDF



Introduced by Priestley, evolutionary spectral theory generalizes the definition of spectrum for nonstationary signals while avoiding some of the shortcomings of bilinear time-frequency distributions. There have been different approaches to estimate Priesley’s evolutionary spectrum such as evolutionary periodogram. In this paper, we present an estimator of evolutionary spectrum for blind separation of nonstationary signals. Our estimator uses a transform based on discrete prolate spheroidal sequences. Also known as Slepian sequences, DPSS are defined to be sequences with maximum spectral concentration for a given duration and bandwidth. Using the connection between discrete evolutionary transform and evolutionary periodogram, we derive the estimator for the evolutionary spectrum and demonstrate its performance for blind source separation of time-varying autoregressive moving average signals



Evolutionary spectrum; Slepian sequences; blind source separation; nonstationary processes



[1] Boashash, B.: 'Time-frequency signal analysis,’ Advances In Spectrum Analysis And Array Processing, vol. 1, S. Haykin, Ed. NJ: Englewood Cliffs Prentice-Hall, (1991).

[2] Priestley, M. B.: 'Power spectral analysis of nonstationary random processes,’ J. Sound Vib, vol. 6, pp. 86–97, (1967).

[3] Kayhan, A., S., El-Jaroudi, A., and Chaparro, L. F.: 'Wold-Cramer evolutionary spectral estimators’, Proc. IEEE-SP Int. Sympos. Time-Frequency Time-Scale Analysis, Victoria, Canada, pp. 115–118, (1992).

[4] Kayhan, A. S., El-Jaroudi, A., and Chaparro, L. F.: 'Evolutionary periodogram for nonstationary Signals,’ IEEE Trans. on Signal Processing, vol. 42, pp. 1527–1536, (1994).

[5] Suleesathira, R., Chaparro, L. F. and Akan, A.: 'Discrete evolutionary transform for timefrequency analysis,’ Proc. Asilomar Conference on Sig., Sys. and Comp., pp. 812–816, (1998).

[6] Kayhan, A. S., and Moeness, G. A.: 'Spatial evolutionary spectrum for DOA estimation and blind signal estimation,’ IEEE Trans. on Signal Processing, vol. 48, pp. 791–797, (2000).

[7] Hosseini, S., and Deville, Y.: 'Blind separation of nonstationary sources by spectral decorrelation,’ In: Puntonet, C.G., Prieto, A.G. (eds.) ICA 2004. LNCS, vol. 3195, pp. 279–286. Springer, Heidelberg (2004).

[8] Johnson, D. H. and Dudgeon, D. E.: 'Array Signal Processing: Concepts and Techniques,’ Englewood Cliffs, NJ: Prentice-Hall, (1993).

[9] Guo, J., Zeng, X., and She, Z.: ' Blind source separation based on high-resolution timefrequency distributions,’ In: Computers and Electrical Engineering, vol. 38, Issue 1, pp. 175– 184, (2012).

[10] Guo, Q., Ruan, G., and Liao, Y.: 'A timefrequency domain underdetermined blind source separation algorithm for MIMO radar signals,’ Symmetry, vol. 9, (2017).

[11] Pal, M., Roy, R., Basu, J. and Bepari, M.: 'Blind source separation: A review and analysis,’ Asian Spoken Language Research and Evaluation Conference, pp. 1–5, (2013).

[12] Belouchrani, A., Meraim, K., Cardoso, J. F., and Moulines, E.: 'A blind source separation techniques using second-order statistics,’ IEEE Trans. Signal Processing, vol. 45, pp. 434–444, (1997).

[13] Belouchrani, A. and Amin, A.: 'Blind source separation based on time-frequency signal representation,’ IEEE Trans. Signal Processing, vol. 46, pp. 2888–2897, (1998).

[14] Sekihara, K, Nagarajan, S., Poeppel, D., and Miyashita, Y.: 'Time-frequency MEG-MUSIC algorithm,’ IEEE Trans. Med. Imag., vol. 18, pp. 92–97, (1999).

[15] Cohen, L.: 'Time-frequency analysis,’ Englewood Cliffs, NJ: Prentice-Hall, (1995).

[16] Bohme, J. F.: 'Array processing in semihomogeneous random fields,’ in Proc. Septieme Colloque Sur le Traitment di Signal est Ses Applications, pp. 104/1–104/4, (1979).

[17] Oh, J., Senay, S. and Chaparro, L. F.: 'Signal reconstruction from nonuniformly spaced samples using evolutionary Slepian transform-based POCS,’ EURASIP Journal on Advances in Signal Processing - Special issue on applications of time-frequency signal processing in wireless communications and bioengineering, (2010).

[18] Slepian, D.: 'Prolate spheroidal wave functions, Fourier Analysis and Uncertainty IV: extensions to many dimensions; generalized prolate spheroidal functions,’ Bell Syst. Techn. Journal, vol. 43, pp. 3009–3057, (1962).

[19] Priestley, M. B.: 'Spectral Analysis and Time Series,’ Academic Press, (1981).

[20] Melard G. and Schutter, A. H.: 'Contributions to evolutionary spectral theory,’ Journal of Time Series Analysis, vol. 10, pp. 41–63, (1989).

[21] Moghtaderi, A., Takahara, G. and Thomson, D. J.: 'Evolutionary spectrum estimation for uniformly modulated processes with improved frequency resolution,’ IEEE Workshop on Statistical Signal Processing, (2009).

[22] Moore, I. C. and Cada, M.: 'Prolate spheroidal wave functions: An introduction to the Slepian series and its properties,’ Applied and Computational Harmonic Analysis, vol. 16, pp. 208–230, (2004).

[23] Walter, G. G. and Shen, X.: 'Sampling with prolate spheroidal functions,’ Am. Math. Soc. Abstract, pp. 41–227, (2003).

[24] Tong, L., Liu. R, Soon, V. and Huang, Y.: ' Indeterminacy and identifiability of blind identification,’ IEEE Trans. on Circuits and Systems, vol. 38, pp. 499–509, (1991).

[25] Fevotte, C. and Doncarli, C.: 'Two contributions to blind source separation using time-frequency distributions,’ IEEE Sig. Pro. Letters, vol. 11, pp. 386–389, (2004).

[26] Cardoso, J. F. and Souloumiac, A.: 'Blind beamforming for non Gaussian signals,’ Proc. Inst. Elect. Eng. vol. 140, pp. 362–370, (1993).

Cite this paper

Seda Senay. (2017) Nonstationary Blind Source Separation Using Slepian Spectral Estimator. International Journal of Signal Processing, 2, 107-114


Copyright © 2017 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0