Circuits, Systems, and Signal Processing

, Volume 36, Issue 10, pp 4145–4160 | Cite as

Sparse Blind Speech Deconvolution with Dynamic Range Regularization and Indicator Function



Blind deconvolution is an ill-posed problem. To solve such a problem, prior information, such as, the sparseness of the source (i.e., input) signal or channel impulse responses, is usually adopted. In speech deconvolution, the source signal is not naturally sparse. However, the direct impulse and early reflections of the impulse responses of an acoustic system can be considered as sparse. In this paper, we exploit the channel sparsity and present an algorithm for speech deconvolution, where the dynamic range of the convolutive speech is also used as the prior information. In this algorithm, the estimation of the impulse response and the source signal is achieved by alternating between two steps, namely, the \(\ell _1\) regularized least squares optimization and a proximal operation. As demonstrated in our experiments, the proposed method provides superior performance for deconvolution of a sparse acoustic system, as compared with two state-of-the-art methods.


Sparse blind deconvolution \(\ell _{1}\) regularized least squares Speech deconvolution Sparse channel estimation 



The work was conducted when J. Guan was visiting the University of Surrey, and supported in part by International Exchange and Cooperation Foundation of Shenzhen City, China (No. GJHZ20150312114149569). W. Wang was supported in part by the Engineering and Physical Sciences Research Council (EPSRC) Grant Number EP/K014307 and the MOD University Defence Research Collaboration in Signal Processing. The authors thank the anonymous reviewers for their helpful suggestions and Dr. Mark Barnard for proofreading the revised manuscript.


  1. 1.
    A. Adiga, C.S. Seelamantula, An alternating \(\ell _p-\ell _2\) projections algorithm (ALPA) for speech modeling using sparsity constraints, in Proceedings of IEEE International Conference on Digital Signal Processing (DSP) (2014), pp. 291–296Google Scholar
  2. 2.
    A. Ahmed, B. Recht, J. Romberg, Blind deconvolution using convex programming. IEEE Trans. Inf. Theory 60(3), 1711–1732 (2014)MathSciNetCrossRefMATHGoogle Scholar
  3. 3.
    A. Alinaghi, P.J. Jackson, Q. Liu, W. Wang, Joint mixing vector and binaural model based stereo source separation. IEEE/ACM Trans. Audio Speech Lang. Process. 22(9), 1434–1448 (2014)CrossRefGoogle Scholar
  4. 4.
    J.B. Allen, D.A. Berkley, Image method for efficiently simulating small-room acoustics. J. Acoust. Soc. Am. 65(4), 943–950 (1979)CrossRefGoogle Scholar
  5. 5.
    A. Benichoux, E. Vincent, R. Gribonval, A fundamental pitfall in blind deconvolution with sparse and shift-invariant priors, in Proceedings of IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP) (2013), pp. 26–31Google Scholar
  6. 6.
    J. Bolte, P.L. Combettes, J.C. Pesquet, Alternating proximal algorithm for blind image recovery, in: Proceedings of IEEE International Conference on Image Processing (ICIP) (2010), pp. 1673–1676Google Scholar
  7. 7.
    S. Boyd, N. Parikh, E. Chu, B. Peleato, J. Eckstein, Distributed optimization and statistical learning via the alternating direction method of multipliers. Found. Trends Mach. Learn. 3(1), 1–122 (2011)CrossRefMATHGoogle Scholar
  8. 8.
    P. Campisi, K. Egiazarian, Blind Image Deconvolution: Theory and Applications (CRC press, Boca Raton, 2007)CrossRefGoogle Scholar
  9. 9.
    R. Chai, G. Naik, T.N. Nguyen, S. Ling, Y. Tran, A. Craig, H. Nguyen, Driver fatigue classification with independent component by entropy rate bound minimization analysis in an EEG-based system. J. Biomed. Health Inform. (2016). doi: 10.1109/JBHI.2016.2532354 Google Scholar
  10. 10.
    Y. Chi, Guaranteed blind sparse spikes deconvolution via lifting and convex optimization. IEEE J. Sel. Top. Signal Process. 10(4), 782–794 (2016)CrossRefGoogle Scholar
  11. 11.
    S. Choudhary, U. Mitra, Fundamental limits of blind deconvolution part I: ambiguity kernel. ArXiv preprint arXiv:1411.3810 (2014)
  12. 12.
    S. Choudhary, U. Mitra, Fundamental limits of blind deconvolution part II: sparsity-ambiguity trade-offs. ArXiv preprint arXiv:1503.03184 (2015)
  13. 13.
    E. Chouzenoux, J.C. Pesquet, A. Repetti, Variable metric forward-backward algorithm for minimizing the sum of a differentiable function and a convex function. J. Optim. Theory Appl. 162(1), 107–132 (2014)MathSciNetCrossRefMATHGoogle Scholar
  14. 14.
    E. Chouzenoux, J.C. Pesquet, A. Repetti, A block coordinate variable metric forward-backward algorithm. J. Glob. Optim. 66(3), 457–485 (2016)MathSciNetCrossRefMATHGoogle Scholar
  15. 15.
    P.L. Combettes, J.C. Pesquet, Proximal splitting methods in signal processing (2009), pp. 1–25.
  16. 16.
    D.L. Donoho, On minimum entropy deconvolution. in Applied Time-Series Analysis II (Academic Press, 1981), pp. 569–609Google Scholar
  17. 17.
    M. Grant, S. Boyd, M. Grant, S. Boyd, V. Blondel, S. Boyd, H. Kimura, CVX: Matlab software for disciplined convex programming, version 2.1. (2014).
  18. 18.
    Y. Guo, S. Huang, Y. Li, G.R. Naik, Edge effect elimination in single-mixture blind source separation. Circuits Syst. Signal Process. 32(5), 2317–2334 (2013)MathSciNetCrossRefGoogle Scholar
  19. 19.
    Y. Guo, G.R. Naik, H. Nguyen, Single channel blind source separation based local mean decomposition for biomedical applications, in Proceedings of the 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 6812–6815 (2013)Google Scholar
  20. 20.
    S. Haykin, Blind Deconvolution (Prentice Hall, Englewood Cliffs, 1994)Google Scholar
  21. 21.
    K.F. Kaaresen, Deconvolution of sparse spike trains by iterated window maximization. IEEE Trans. Signal Process. 45(5), 1173–1183 (1997)CrossRefGoogle Scholar
  22. 22.
    K.F. Kaaresen, T. Taxt, Multichannel blind deconvolution of seismic signals. Geophysics 63(6), 2093–2107 (1998)CrossRefGoogle Scholar
  23. 23.
    C. Kelley, Iterative methods for linear and nonlinear equations. SIAM Front. Appl. Math. 16, 11–30 (1995)Google Scholar
  24. 24.
    S.J. Kim, K. Koh, M. Lustig, S. Boyd, D. Gorinevsky, An interior-point method for large-scale \(\ell _1\)-regularized least squares. IEEE J. Sel. Top. Signal Process. 1(4), 606–617 (2007)CrossRefGoogle Scholar
  25. 25.
    D. Krishnan, T. Tay, R. Fergus, Blind deconvolution using a normalized sparsity measure, in Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2011), pp. 233–240Google Scholar
  26. 26.
    X. Li, S. Ling, T. Strohmer, K. Wei, Rapid, robust, and reliable blind deconvolution via nonconvex optimization. ArXiv preprint arXiv:1606.04933 (2016)
  27. 27.
    H. Liu, S. Liu, T. Huang, Z. Zhang, Y. Hu, T. Zhang, Infrared spectrum blind deconvolution algorithm via learned dictionaries and sparse representation. Appl. Opt. 55(10), 2813–2818 (2016)CrossRefGoogle Scholar
  28. 28.
    Y. Luo, W. Wang, J.A. Chambers, S. Lambotharan, I. Proudler, Exploitation of source nonstationarity in underdetermined blind source separation with advanced clustering techniques. IEEE Trans. Signal Process. 54(6), 2198–2212 (2006)CrossRefGoogle Scholar
  29. 29.
    G. Naik, A. Al-Timemy, H. Nguyen, Transradial amputee gesture classification using an optimal number of sEMG sensors: an approach using ICA clustering. IEEE Trans. Neural Syst. Rehabil. Eng. 24(8), 837–846 (2016)CrossRefGoogle Scholar
  30. 30.
    G. Naik, S. Selvan, H. Nguyen, Single-channel EMG classification with ensemble-empirical-mode-decomposition-based ICA for diagnosing neuromuscular disorders. IEEE Trans. Neural Syst. Rehabil. Eng. 24(7), 734–743 (2016)CrossRefGoogle Scholar
  31. 31.
    G.R. Naik, Enhancement of the ill-conditioned original recordings using novel ICA technique. Int. J. Electron. 99(7), 899–906 (2012)CrossRefGoogle Scholar
  32. 32.
    G.R. Naik, D.K. Kumar, Estimation of independent and dependent components of non-invasive EMG using fast ICA: validation in recognising complex gestures. Comput. Methods Biomech. Biomed. Eng. 14(12), 1105–1111 (2011)CrossRefGoogle Scholar
  33. 33.
    N. Parikh, S. Boyd, Proximal algorithms. Found. Trends Optim. 1(3), 127–239 (2014)CrossRefGoogle Scholar
  34. 34.
    G. Pendharkar, G.R. Naik, H.T. Nguyen, Using blind source separation on accelerometry data to analyze and distinguish the toe walking gait from normal gait in ITW children. Biomed. Signal Process. Control 13, 41–49 (2014)CrossRefGoogle Scholar
  35. 35.
    A. Repetti, E. Chouzenoux, J.C. Pesquet, A preconditioned forward–backward approach with application to large-scale nonconvex spectral unmixing problems, in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2014), pp. 1498–1502Google Scholar
  36. 36.
    A. Repetti, M.Q. Pham, L. Duval, E. Chouzenoux, J.C. Pesquet, Euclid in a taxicab: sparse blind deconvolution with smoothed regularization. IEEE Signal Process. Lett. 22(5), 539–543 (2015)CrossRefGoogle Scholar
  37. 37.
    I. Selesnick, Sparse deconvolution (an MM algorithm). (2012)
  38. 38.
    R. Tibshirani, Regression shrinkage and selection via the lasso. J. R. Stat. Soc. Ser. B (Methodological) 58(1), 267–288 (1996)Google Scholar
  39. 39.
    E. Vincent, R. Gribonval, C. Févotte, Performance measurement in blind audio source separation. IEEE Trans. Audio Speech Lang. Process. 14(4), 1462–1469 (2006)CrossRefGoogle Scholar
  40. 40.
    L. Wang, Y. Chi, Blind deconvolution from multiple sparse inputs. IEEE Signal Process. Lett. 23(10), 1384–1388 (2016)MathSciNetCrossRefGoogle Scholar
  41. 41.
    W. Wang, M.G. Jafari, S. Sanei, J.A. Chambers, Blind separation of convolutive mixtures of cyclostationary signals. Int. J. Adapt. Control Signal Process. 18(3), 279–298 (2004)CrossRefMATHGoogle Scholar
  42. 42.
    W. Wang, S. Sanei, J.A. Chambers, Penalty function-based joint diagonalization approach for convolutive blind separation of nonstationary sources. IEEE Trans. Signal Process. 53(5), 1654–1669 (2005)MathSciNetCrossRefGoogle Scholar
  43. 43.
    T. Xu, W. Wang, W. Dai, Sparse coding with adaptive dictionary learning for underdetermined blind speech separation. Speech Commun. 55(3), 432–450 (2013)CrossRefGoogle Scholar
  44. 44.
    Y. Yu, W. Wang, P. Han, Localization based stereo speech source separation using probabilistic time-frequency masking and deep neural networks. EURASIP J. Audio Speech Music Process. 2016(1), 1–18 (2016)CrossRefGoogle Scholar
  45. 45.
    H. Zhang, D. Wipf, Y. Zhang, Multi-observation blind deconvolution with an adaptive sparse prior. IEEE Trans. Pattern Anal. Mach. Intell. 36(8), 1628–1643 (2014)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.Harbin Institute of Technology Shenzhen Graduate SchoolShenzhenChina
  2. 2.Centre for Vision, Speech and Signal ProcessingUniversity of SurreyGuildfordUK
  3. 3.College of Information EngineeringShenzhen UniversityShenzhenChina

Personalised recommendations