Least Squares Filtering of Speech Signals for Robust ASR

  • Vivek Tyagi
  • Christian Wellekens
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3869)


The behavior of the least squares filter (LeSF) is analyzed for a class of non-stationary signals that are composed of multiple sinusoids whose frequencies, phases and the amplitudes may vary from block to block and which are embedded in white noise. Analytic expressions for the weights and the output of the LeSF are derived as a function of the block length and the signal SNR computed over the corresponding block. Recognizing that such a sinusoidal model is a valid approximation to the speech signals, we have used LeSF filter estimated on each block to enhance the speech signals embedded in white noise. Automatic speech recognition (ASR) experiments on a connected numbers task, OGI Numbers95[20] show that the proposed LeSF based features yield an increase in speech recognition performance in various non-stationary noise conditions when compared directly to the un-enhanced speech and noise robust JRASTA-PLP features.


Speech Signal Automatic Speech Recognition Frame Length Noisy Speech Automatic Speech Recognition System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Satorius, E., Zeidler, J., Alexander, S.: Linear predictive digital filtering of narrowband processes in additive broad-band noise. Naval Ocean Systems Center, San Diego, CA, Tech. Rep. 331 (November 1978)Google Scholar
  2. 2.
    Anderson, C.M., Satorius, E.H., Zeidler, J.R.: Adaptive Enhancement of Finite Bandwidth Signals in White Gaussian Noise. IEEE Trans. on ASSP ASSP-31(1) (February 1983)Google Scholar
  3. 3.
    Zeidler, J.R., Satorius, E.H., Chabries, D.M., Wexler, H.T.: Adaptive Enhancement of Multiple Sinusoids in Uncorrelated Noise. IEEE Trans. on ASSP ASSP-26(3) (June 1978)Google Scholar
  4. 4.
    Hermansky, H., Morgan, N.: Rasta Processing of Speech. IEEE Trans. on SAP 2(4) (October 1994)Google Scholar
  5. 5.
    Sambur, M.R.: Adaptive noise canceling for Speech signals. IEEE Trans. on ASSP ASSP-26(5) (October 1978)Google Scholar
  6. 6.
    Haykin, S.: Adaptive Filter Theory. Prentice-Hall Publishers, NJ (1993)zbMATHGoogle Scholar
  7. 7.
    McAulay, R.J., Quatieri, T.F.: Speech Analysis/Synthesis Based on a Sinusoidal Representation. IEEE Trans. on ASSP ASSP-34(4) (August 1986)Google Scholar
  8. 8.
    Widrow, B., et al.: Adaptive noise cancelling: Principles and applications. Proc. IEEE 65, 1692–1716 (December 1975)CrossRefGoogle Scholar
  9. 9.
    Sondhi, M., Berkley, D.: Silencing echoes on the telephone network. Proc. of IEEE 68, 948–963 (August 1980)CrossRefGoogle Scholar
  10. 10.
    Gersho, A.: Adaptive equalization of highly dispersive channels for data transmission. Bell Syst. Tech. J. 48, 55–70 (January 1969)CrossRefzbMATHGoogle Scholar
  11. 11.
    Satorius, E., Alexander, S.T.: Channel equalization using adaptive lattice algorithms. IEEE Trans. Commun. 27, 899–905 (June 1979)CrossRefzbMATHGoogle Scholar
  12. 12.
    Satorius, E., Pack, J.: Application of least squares lattice algorithms for adaptive equalization. IEEE Trans. on Commun. COM-29, 136–142 (February 1981)CrossRefGoogle Scholar
  13. 13.
    Bershad, N., Feintuch, P., Reed, F., Fisher, B.: Tracking characteristics of the LMS adaptive line-enhancer -Response to a linear chirp signal in noise. IEEE Trans. on ASSP ASSP-28, 504–517 (October 1980)CrossRefGoogle Scholar
  14. 14.
    Griffiths, L.J.: A simple adaptive algorithm for real time processsing in antenna arrays. Proc. of IEEE 57, 1696–1704 (October 1969)CrossRefGoogle Scholar
  15. 15.
    Frost, O.L.: An algorithm for linearly constrained adaptive array processing. Proc. of IEEE 60, 926–935 (August 1972)CrossRefGoogle Scholar
  16. 16.
    Marple, L.: Efficient least squares FIR system identification. IEEE Trans. on ASSP ASSP-29, 62–73 (February 1981)CrossRefGoogle Scholar
  17. 17.
    Davis, S.B., Mermelstein, P.: Comparison of Parametric Representation for Monosyllabic Word Recognition in Continuously Spoken Sentences. IEEE Trans. on ASSP ASSP-28(4) (August 1980)Google Scholar
  18. 18.
    Young, S., Odell, J., Ollason, D., Valtchev, V., Woodland, P.: The HTK Book. Cambridge University, Cambridge (1995)Google Scholar
  19. 19.
    Cole, R.A., Fanty, M., Lander, T.: Telephone speech corpus at CSLU. In: Proc. of ICSLP, Yokohama, Japan (1994)Google Scholar
  20. 20.
    Varga, A., Steeneken, H., Tomlinson, M., Jones, D.: The NOISEX-92 study on the effect of additive noise on automatic speech recognition. Technical report, DRA Speech Research Unit, Malvern, England (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Vivek Tyagi
    • 1
    • 2
  • Christian Wellekens
    • 1
    • 2
  1. 1.Institute Eurecom, Sophia-AntipolisFrance
  2. 2.Swiss Federal Institute of Technology (EPFL)LausanneSwitzerland

Personalised recommendations