A Nonlinear Acoustic Echo Canceller with Improved Tracking Capabilities

  • Danilo Comminiello
  • Michele Scarpiniti
  • Simone Scardapane
  • Raffaele Parisi
  • Aurelio Uncini
Chapter

Abstract

Thispaperintroduces the use of a variable step size for a functional link adaptive filter (FLAF). We consider a split FLAF architecture, in which linear and nonlinear filterings are performed in two separate paths, thus resulting well-suited for online filtering applications, like the nonlinear acoustic echo cancellation (NAEC). We focus our attention on the nonlinear path to improve the overall NAEC performance. To this end, we derive a variable step size for the filter on the nonlinear path that shows reliance not only on the nonlinear path, but on the whole split FLAF architecture. The introduction of the variable step size for the nonlinear filter aims at improving the modeling of nonlinear speech signals, thus yielding superior performance in NAEC problems. Experimental results prove the effectiveness of the proposed method with respect to the standard split FLAF involving a fixed step size.

Keywords

Functional links Nonlinear acoustic echo cancellation Nonlinear adaptive filtering Nonlinear speech modeling 

References

  1. 1.
    Aboulnasr, T., Mayyas, K.: A robust variable step-size LMS-type algorithm: analysis and simulations. IEEE Trans. Signal Process. 45(3), 631–639 (1997)CrossRefGoogle Scholar
  2. 2.
    Albu, F., Coltuc, D., Comminiello, D., Scarpiniti, M.: The variable step size regularized block exact affine projection algorithm. In: Proceedings of the IEEE International Symposium on Electronics and Telecommunications (ISETC), pp. 283–286. Timisoara, Romania, Nov 2012Google Scholar
  3. 3.
    Benesty, J., Rey, H., Vega, L.R., Tressens, S.: A nonparametric VSS NLMS algorithm. IEEE Signal Process. Lett. 13(10), 581–584 (2006)CrossRefGoogle Scholar
  4. 4.
    Comminiello, D., Azpicueta-Ruiz, L.A., Scarpiniti, M., Uncini, A., Arenas-García, J.: Functional link based architectures for nonlinear acoustic echo cancellation. In: Proceedings of the IEEE Joint Workshop on Hands-free Speech Communication and Microphone Arrays (HSCMA), pp. 180–184. Edinburgh, UK, May 2011Google Scholar
  5. 5.
    Comminiello, D., Scarpiniti, M., Azpicueta-Ruiz, L.A., Arenas-García, J., Uncini, A.: Functional link adaptive filters for nonlinear acoustic echo cancellation. IEEE Trans. Audio Speech Lang. Process. 21(7), 1502–1512 (2013)CrossRefGoogle Scholar
  6. 6.
    Comminiello, D., Scarpiniti, M., Azpicueta-Ruiz, L.A., Arenas-García, J., Uncini, A.: Nonlinear acoustic echo cancellation based on sparse functional link representations. IEEE/ACM Trans. Audio Speech Lang. Process. 7(22), 1172–1183 (2014)CrossRefGoogle Scholar
  7. 7.
    Comminiello, D., Scardapane, S., Scarpiniti, M., Parisi, R., Uncini, A.: Functional Link Expansions for Nonlinear Modeling of Audio and Speech Signals. In: Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), pp. 1–8. Killarney, Ireland, Jul 2015Google Scholar
  8. 8.
    Comminiello, D., Scarpiniti, M., Parisi, R., Uncini, A.: A novel affine projection algorithm for superdirective microphone array beamforming. In: Proceedings of the IEEE International Symposium on Circuits and Systems (ISCAS), pp. 2127–2130. Paris, France, May 2010Google Scholar
  9. 9.
    Comminiello, D., Scarpiniti, M., Parisi, R., Uncini, A.: Convergence properties of nonlinear functional link adaptive filters. IET Electron. Lett. 49(14), 873–875 (2013)CrossRefGoogle Scholar
  10. 10.
    Comminiello, D., Scarpiniti, M., Scardapane, S., Parisi, R., Uncini, A.: Improving nonlinear modeling capabilities of functional link adaptive filters. Neural Networks 69, 51–59 (2015)CrossRefGoogle Scholar
  11. 11.
    Huang, H.C., Lee, J.: A new variable step-size nlms algorithm and its performance analysis. IEEE Trans. Signal Process. 60(4), 2055–2060 (2012)CrossRefMathSciNetGoogle Scholar
  12. 12.
    Paleologu, C., Benesty, J., Ciochină, S.: A variable step-size affine projection algorithm designed for acoustic echo cancellation. IEEE Trans. Audio Speech Lang. Process. 16(8), 1466–1478 (2008)CrossRefGoogle Scholar
  13. 13.
    Vega, Rey: L., Rey, H., Benesty, J., Tressens, S.: A new robust variable step-size nlms algorithm. IEEE Trans. Signal Process. 56(5), 1878–1893 (2008)CrossRefMathSciNetGoogle Scholar
  14. 14.
    Sayed, A.H.: Adaptive Filters. John Wiley & Sons, Hoboken, NJ (2008)CrossRefGoogle Scholar
  15. 15.
    Shin, H.C., Sayed, A.H., Song, W.J.: Variable step-size NLMS and adffine projection algorithms. IEEE Signal Process. Lett. 11(2), 132–135 (2004)CrossRefGoogle Scholar
  16. 16.
    Uncini, A.: Fundamentals of Adaptive Signal Processing. Springer International Publishing AG, Cham, Switzerland, Signal and Communication Technology (2015)CrossRefMATHGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Danilo Comminiello
    • 1
  • Michele Scarpiniti
    • 1
  • Simone Scardapane
    • 1
  • Raffaele Parisi
    • 1
  • Aurelio Uncini
    • 1
  1. 1.Department of Information EngineeringElectronics and Telecommunications (DIET) “Sapienza” University of RomeRomeItaly

Personalised recommendations