Detecting Broad Phonemic Class Boundaries from Greek Speech in Noise Environments

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4188)


In this work, we present the performance evaluation of an implicit approach for the automatic segmentation of continuous speech signals into broad phonemic classes as encountered in Greek language. Our framework was evaluated with clear speech and speech with white, pink, bubble, car and machine gun additive noise. Our framework’s results were very promising since an accuracy of 76.1% was achieved for the case of clear speech (for distances less than 25 msec to the actual segmentation point), without presenting over-segmentation on the speech signal. An average reduction of 4% in the total accuracy of our segmentation framework was observed in the case of wideband distortion additive noise environment.


Speech Signal Automatic Segmentation Dynamic Time Warping Clear Speech Pitch Contour 
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.
    Young, S., Kershaw, D., Odell, J., Ollason, D., Valtchev, V., Woodland P.: The HTK Book, Revised for HTK Version 3.0 (July 2000)Google Scholar
  2. 2.
    Zissman, M.: Comparison of four Approaches to Automatic Language Identification of Telephone Speech. IEEE Trans. Speech and Audio Proc. SAP-4, 31–44 (1996)CrossRefGoogle Scholar
  3. 3.
    Dutoit, T.: An Introduction to Text-To-Speech Synthesis. In: Text, Speech and Language Technology, vol. 3. Kluwer Academic Publishers, Dordrecht (1997)Google Scholar
  4. 4.
    van Hemert, J.: Automatic Segmentation of Speech. IEEE Transactions on Signal Processing 39(4) (April 1991)Google Scholar
  5. 5.
    Aversano, G., Esposito, A., Esposito, A., Marinaro, M.: A new text-independent method for phoneme segmentation. In: Proc. of 44th IEEE Midwest Symp. Circuits and Systems, vol. 2, pp. 516–519 (2001)Google Scholar
  6. 6.
    Suh, Y., Lee, Y.: Phoneme segmentation of continuous speech using multi-layer perceptron. In: Proc. of ICSLP 1996, pp. 1297–1300 (1996)Google Scholar
  7. 7.
    Svendsen, T., Kvale, K.: Automatic alignment of phonemic labels in continuous speech. In: Proc. of ICSLP 1990, Kobe, Japan (1990)Google Scholar
  8. 8.
    Svendsent, T., Soong, F.K.: On the automatic segmentation of speech signals. In: Proc. of ICASSP 1987, Dallas, pp. 77–80 (April 1987)Google Scholar
  9. 9.
    Grayden, D., Scordilis, M.: Phonemic segmentation of fluent speech. In: Proc. of ICASSP 1994, pp. 73–76 (1994)Google Scholar
  10. 10.
    Essa, O.: Using prosody in automatic segmentation of speech. In: Proc. of 36th ACM Southeast Regional Conference (1998)Google Scholar
  11. 11.
    Pellom, B., Hansen, J.: Automatic segmentation of speech recorded in unknown noisy channel characteristics. Speech Communication 25, 97–116 (1998)CrossRefGoogle Scholar
  12. 12.
    Reddy, D.R.: Pitch Period Determination of Speech Sounds. Communication of the ACM 10, 343–348 (1967)Google Scholar
  13. 13.
  14. 14.
    Boersma, P.: Accurate short-term analysis of the fundamental frequency and the harmonics-to-noise ratio of a sampled sound. In: Proc. of IFA,, vol. 17, pp. 97–110 (1993)Google Scholar
  15. 15.
    Boersma, P., Weenink, D.: Praat: doing phonetics by computer (2005), Retrieved from:
  16. 16.
    Deller, J., Proakis, J., Hansen, J.: Discrete-time processing of speech signals. MacMillan Series. Prentice-Hall Publishers, New York (1993)Google Scholar
  17. 17.
    Zervas, P., Fakotakis, N., Kokkinakis, G.: Development of a prosodic database for Greek speech synthesis. In: Proc. of SPECOM 2005, Patras, Greece, pp. 603–606 (2005)Google Scholar
  18. 18.
    Varga, A., Steenneken, H., J., M., Tomlinson, M., Jones, D.: The NOISEX 1992 study on the effect of additive noise on automatic speech recognition (1992)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  1. 1.Wire Communications Laboratory, Electrical and Computer Engineering DepartmentUniversity of PatrasPatrasGreece

Personalised recommendations