Advertisement

Circuits, Systems and Signal Processing

, Volume 15, Issue 1, pp 71–92 | Cite as

Sequential speech segmentation based on the spectral ARMA transition measure

  • Srbijanka R. Turajlić
  • Zoran M. Šarić
Article

Abstract

Sequential segmentation algorithms based on the AR model tend to produce false alarms or to omit the change for sequences that corresponds to the ARMA model. In this paper a new sequential segmentation algorithm based on the ARMA model is presented. The ARMA model is estimated over the relatively short sequence, which has called for the implementation of the estimation algorithm with appropriately initialized starting values. The proposed algorithm adopts the MGLR concept of the sliding reference and test windows, which allow the process of decision making to be separated from the evaluation of the discrimination function. This has enabled the new triangular decision rule to be proposed; this is based on the expected shape of the discrimination function at the time of the model change. Two possible discrimination functions have been suggested. One of them is optimal in the statistical sense; the other has the better asymptotic behavior. Natural speech signal segmentation is also discussed, and an appropriate pitch-synchronous signal prearrangement has been suggested. This not only enhances the segmentation algorithm but also increases its speed, as the time can be increased by a step equal to the pitch period. The segmentation algorithm is verified on test signals as well as on the natural speech signal. The experimental results also include a comparison of the sequential AR and ARMA model-based segmentation.

Keywords

False Alarm Estimation Algorithm Decision Rule Segmentation Algorithm Short Sequence 
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.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    R. Andre-Obrecht, On-line segmentation of speech signals without prior recognition, inDetection of Abrupt Changes in Signals and Dynamical Systems, eds. M. Basseville and A. Benveniste, Springer-Verlag, Berlin and New York, 1980.Google Scholar
  2. [2]
    U. Appel and A. V. Brandt, Adaptive sequential segmentation of piecewise stationary time series,Inform. Sci., vol. 29, 1983, pp. 27–56.Google Scholar
  3. [3]
    Detection of Abrupt Changes in Signals and Dynamical Systems, eds. M. Basseville and A. Beneviste, Springer-Verlag, Berlin and New York, 1986.Google Scholar
  4. [4]
    B. Friedlander, Lattice filters for adaptive processing,Proc. IEEE, vol. 70, no. 8, Aug. 1982, pp. 892–1017.Google Scholar
  5. [5]
    W. Hess,Pitch Determination of Speech Signals, Springer-Verlag, Berlin and New York, 1983.Google Scholar
  6. [6]
    I. Konvalinka and M. R. Mataušek, Simultaneous estimation of poles and zeros in speech analysis and ITIF — Iterative Inverse Filtering Algorithm,IEEE Trans. Acoust. Speech Signal Process., vol. ASSP-27, Oct. 1979, pp. 485–491.Google Scholar
  7. [7]
    I. Konvalinka and M. Milosavljević, Sequential detection of abrupt changes in the digital signals,Proc. XXX ETAN Conf., Herceg-Novi, June 1986 (in Serbian).Google Scholar
  8. [8]
    J. D. Markel and A. H. Gray, Jr.,Linear Prediction of Speech, Springer-Verlag, Berlin and New York, 1976.Google Scholar
  9. [9]
    M. R. Mataušek, S. S. Stanković, and D. V. Radović, Iterative inverse filtering approach to the estimation of frequencies of noisy sinusoids,IEEE Trans. Acoust. Speech Signal Process., vol. ASSP-31, Dec. 1983.Google Scholar
  10. [10]
    Y. Miyoshi, K. Yamato, R. Mizoguchi, M. Yanagida, and O. Kakusho, Analysis of speech signals of short pitch period by a sample-selective linear prediction,IEEE Trans. Acoust. Speech Signal Process., vol. ASSP-35, no. 9, pp. 1233–1239, September 1987.Google Scholar
  11. [11]
    I. V. Nikiforor, ed.,Sequential Detection of Abrupt Changes in Time Series Properties, “Nauka,” Moscow, 1983.Google Scholar
  12. [12]
    Z. M. Šarić, The abrupt change detection in the signals with the ARMA structure, Ph.D. dissertation, EE Dept., University of Belgrade, 1994 (in Serbian).Google Scholar
  13. [13]
    Z. Šarić and M. Milosavljević, Correlation approach in the detection of abrupt changes in the MGLR algorithm,Proc. XV Symp. on Inf. Technology, Sarajevo, March 1991, 251-1–254-8 (in Serbian).Google Scholar
  14. [14]
    Z. M. Šarić and S. R. Turajlić, Estimation and setting starting values in ARMA algorithms,Circuits Systems Signal Process., vol. 12, no. 1, 1993, pp. 85–103.Google Scholar
  15. [15]
    Y. Shiraki and M. Honda, LPC speech coding based on variable length segment quantization,IEEE Trans. Acoust. Speech Signal Process., vol. 36, no. 9, Sept. 1988, pp. 1437–1444.Google Scholar
  16. [16]
    T. Svedsen and F. K. Soong, On the automatic segmentation of speech signals,IC ASSP 1987, pp. 77–80.Google Scholar
  17. [17]
    E. Vidal and A. Marzal, A review and new approaches for automatic segmentation of speech signal,Proc. of EUSIPCO-90, Barcelona (Spain), Sept. 1990, vol. 1, pp. 43–54.Google Scholar
  18. [18]
    P. De Souza and P.J. Thomson, LPL distance measures and statistical tests with particular reference to the likelihood ratio,IEEE Trans. ASSP, vol. ASSP-30, no. 2, pp. 304–315, April 1982.Google Scholar

Copyright information

© Birkhäuser 1996

Authors and Affiliations

  • Srbijanka R. Turajlić
    • 1
  • Zoran M. Šarić
    • 1
  1. 1.Department of Electrical EngineeringUniversity of BelgradeBeogradYugoslavia

Personalised recommendations