Recognition of Repetition and Prolongation in Stuttered Speech Using ANN

  • P. S.  Savin
  • Pravin B. Ramteke
  • Shashidhar G. Koolagudi
Conference paper
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 43)


This paper mainly focuses on repetition and prolongation detection in stuttered speech signal. The acoustic and pitch related features like Mel-frequency cepstral coefficients (MFCCs), formants, pitch, zero crossing rate (ZCR) and Energy are used to test the effectiveness in recognizing repetitions and prolongations in stammered speech. Artificial Neural Networks (ANN) are used as classifier. The results are evaluated using combination of different features. The results show that the ANN classifier trained using MFCC features achieves an average accuracy of 87.39 % for repetition and prolongation recognition.


ANN Energy Formants MFCCs Pitch Zero crossing rate 


  1. 1.
    Van Riper, C.: The Nature of Stuttering. Prentice Hall, New Jersey (1971)Google Scholar
  2. 2.
    Czyzewski, Andrzej, Kaczmarek, Andrzej, Kostek, Bozena: Intelligent processing of stuttered speech. J. Intell. Inf. Syst. 21, 143–171 (2003)CrossRefGoogle Scholar
  3. 3.
    Kully, D., Boerg, E.: An investigation of inter-clinic agreement in the identification of fluent and stuttered syllables. J. Fluency disord. 13, 309–318 (1988)CrossRefGoogle Scholar
  4. 4.
    Conture, E.: International Conference on Intelligent and Advanced Systems, 2nd edn. Prentice-Hall, Englewood Cliffs (1990)Google Scholar
  5. 5.
  6. 6.
    Zhang, J., Dong, B., Yan, Y.: A computer-assist algorithm to detect repetitive stuttering automatically. In: International Conference on Asian Language Processing, pp. 249–252 (2013)Google Scholar
  7. 7.
    Sin Chee, L., Chia Ai, O., Hariharan, M.: MFCC based recognition of repetition and prolongations in stuttered speech using artificial k-nn and lda. In: IEEE Student Conference on Research and Development, pp. 146–149 (2009)Google Scholar
  8. 8.
    Ravikumar, K.M., Rajagopal, R., Nagaraj, H.C.: An approach for objective assessment of stuttered speech using MFCC features. ICGST Int. J. Digital Signal Process. 9, 19–24 (2009)Google Scholar
  9. 9.
    Chia Ai, O., Hariharan, M., Yaacob, S., Sin Chee, L.: Classification of speech dysfluencies with MFCC and LPCC features. J. Med. Syst. 39, 2157–2165 (2012)Google Scholar
  10. 10.
    Wisniewski, M., Kuniszyk, J.W., Smolka, E., Suszynski, W.: Automatic detection of disorders in a continuous speech with the hidden markov models approach. Comput. Recogn. Syst. 2(45), 445–453 (2007)CrossRefGoogle Scholar
  11. 11.
    Sin Chee, L., Chia Ai, O., Hariharan, M., Yaacob, S.: Automatic detection of prolongations and repetitions using LPCC. In; 2009 International Conference Technical Postgraduates (TECHPOS) (2009)Google Scholar
  12. 12.
    Tan, T.S., Liboh, H., Ariff, A.K., Ting, C.M., Salleh, H.: Application of malay speech technology in malay speech therapy assistance tools. Int. Conf. Intell. Adv. Syst. 48, 330–334 (2007)Google Scholar
  13. 13.
    Ravikumar, K.M., Balakrishna Reddy, Rajagopal, R., Nagaraj, H.C.: Automatic detection of syllable repetition in read speech for objective assessment of stuttered disfluencies. Proce. World Acad. Sci. 2, 220–223 (2008)Google Scholar
  14. 14.
    Rabiner, L., Juang, B., Yegnanarayana, B.: Fundamentals of Speech Recognition. Pearson, India (2010)Google Scholar
  15. 15.
    Welling, L., Ney, H.: Formant estimation for speech recognition. IEEE Trans. Speech Audio Process. 6, 36–48 (1998)CrossRefGoogle Scholar
  16. 16.
    IIT Guwahati.: Estimation of pitch from speech signal.
  17. 17.
    Gevaert, W., Tsenov, G., Mladenov, V.: Neural networks used for speech recognition. J. Autom. Control 2, 732–735 (2010)Google Scholar

Copyright information

© Springer India 2016

Authors and Affiliations

  • P. S.  Savin
    • 1
  • Pravin B. Ramteke
    • 1
  • Shashidhar G. Koolagudi
    • 1
  1. 1.National Institute of Technology KarnatakaSurathkalIndia

Personalised recommendations