The Prolongation-Type Speech Non-fluency Detection Based on the Linear Prediction Coefficients and the Neural Networks

  • Adam KobusEmail author
  • Wiesłwa Kuniszyk-Jóźkowiak
  • Elżbieta Smołka
  • Ireneusz Codello
  • Waldemar Suszyński
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 226)


The goal of the paper is presenting a speech prolongation detection method based on the linear predicion coefficients obtained by the Levinson-Durbin method. The application “Dabar”, which was made for this aim, has an ability of setting the coefficients computed by the implemented methods as an input of the Kohonen networks with different size of the output layer. Three different types of the neural networks were used to classify fluency of the utterances: RBF networks, linear networks and Multi-Layer Perceptrons. The Kohonen network (SOM) was used to reduce the LP coefficients representation to the winning neurons vector. After that the vector was splitted into subvectors whom represents 400ms utterances. These utterances were fragments of the Polish speech without the silence. The research was based on 202 fluent utterances and 140 with the prolongations on Polish phonems. The classifying success reached 75% of certainty.


Hide Layer Radial Basis Function Output Layer Speech Signal Radial Basis Function Network 
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.
    Buhmann, M.D.: Radial Basis Functions: Theory and Implementations. Cambridge University, Cambridge (2003)CrossRefGoogle Scholar
  2. 2.
    Codello, I., Kuniszyk-Jóźkowiak, W.: Digital signals analysis with the LPC method. Annales UMCS Informatica 5, 315–321 (2006)Google Scholar
  3. 3.
    Duch, W., Korbicz, J., Rutkowski, L., Tadeusiewicz, R.: Biocybernetyka i inżynieria biomedyczna, - t. 6. Sieci neuronowe. Akademicka Oficyna Wydawnicza EXIT, Warszawa (2000) (in Polish)Google Scholar
  4. 4.
    Kobus, A., Kuniszyk-Jóźkowiak, W., Smołka, E., Codello, I.: Speech nonfluency detection and classification based on linear prediction coefficients and neural networks. Medical Informatics & Technologies 15, 135–144 (2010)Google Scholar
  5. 5.
    Kohonen, T.: Self-Organising Maps, 3rd edn. Springer, Berlin (2001)CrossRefGoogle Scholar
  6. 6.
    Rabiner, L.R., Schafer, R.W.: Digital Processing of Speech Signals. Prentice Hall, New Jersey (1978)Google Scholar
  7. 7.
    Suszyński, W.: Komputerowa analiza i rozpoznawanie mowy. Politechnika Iska, Gliwice (2005) (in Polish)Google Scholar
  8. 8.
    Szczurowska, I., Kuniszyk-Jóźkowiak, W., Smołka, E.: Speech nonfluency detection using Kohonen networks. Neural Computing & Applications (2009)Google Scholar
  9. 9.
    Tadeusiewicz, R.: Sieci neuronowe. Akademicka Oficyna Wydawnicza RM, Warszawa (1993) (in Polish)Google Scholar
  10. 10.
    Tebelskis, J.: Speech Recognition using Neural Networks. Carnegie Mellon University, Pittsburgh (1995)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2013

Authors and Affiliations

  • Adam Kobus
    • 1
    Email author
  • Wiesłwa Kuniszyk-Jóźkowiak
    • 1
    • 2
  • Elżbieta Smołka
    • 1
  • Ireneusz Codello
    • 1
  • Waldemar Suszyński
    • 1
  1. 1.Institute of Computer ScienceMarie Curie-Skłodowska UniversityLublinPoland
  2. 2.Faculty of Physical Education and Sport in Biała PodlaskaBiała PodlaskaPoland

Personalised recommendations