Open Access Journal

ISSN : 2394 - 6849 (Online)

International Journal of Engineering Research in Electronics and Communication Engineering(IJERECE)

Monthly Journal for Electronics and Communication Engineering

Open Access Journal

International Journal of Engineering Research in Electronics and Communication Engineering(IJERECE)

Monthly Journal for Electronics and Communication Engineering

ISSN : 2394-6849 (Online)

Automatic Recognition for Instances of Repetitions in Stuttered Speech using Sequence Training Algorithm

Author : G. Manjula 1 Dr. M. Shiva Kumar 2

Date of Publication :7th May 2016

Abstract: Stuttering is a speech disorder in which normal flow of speech is messed out by occurrences of dysfluencies. There are high proportion of prolongations and repetitions in stuttered speech. Stuttered speech recognition technology is a great aid to admit the challenges and it is a prominent technology for Human-computer Interaction . Conventionally, stuttering assessment is done by counting number of dysfluent words as a proportion of total words in a passage. Stuttering assessment is also done by measuring the time of dysfluencies and comparing with the duration of the entire passage. However, it is time-consuming and it results in poor agreement with different individuals assessing the same speech data. Therefore, automatic stuttered speech recognition system is used to automate the dysfluency count and type of dysfluency classification, thus providing an objective and consistent assessment of stuttered speech. Such approach can support Speech Language Pathology (SLP) by doing tedious routine works and allowing more time for therapeutic session between SLP and stutterers. Instances of repetitions in stuttered speech are recognized by using back propogation based sequence training method. Artificial neural network is used to make intelligence through the learning process. In this work Multi-layer Feed forward Network and error back propagation learning algorithm is used to train the network. The combination of the artificial neural network and the back propagation algorithm is the sequence training technique. The experimental investigations reveal that the proposed method shows promising results in identifying the instances of repetitions in stuttered speech

Reference :

  1. [1] Andrzej Czyzewski, Andrzej Kaczmarek1and Bozena Kostek, “Intelligent processing of stuttered speech”, Journal of Intelligent Information Systems, 10.1.1.109.715, 2003

    [2] Hariharan.M, Vijean.V, Fook.C.Y, Yaacob.S, “Speech stuttering assessment using sample entropy and Least Square Support Vector Machine”, Signal Processing and its Applications (CSPA)”, ISBN: 978-1-4673-0960-8, pp. 240- 245, 2012

    [3] Michael D. McClean, D.C. Stephen M. Tasko,MI Charles M. Runyan James “Orofacial Movements Associated With Fluent Speech in Persons Who Stutter” Journal of Speech, Language, and Hearing Research,Vol. 47, pp 294–303, April 2004 ©American Speech-LanguageHearing Association 1092-4388/04/4702-0294

    [4] Jiang J, Lu C, Peng D, Zhu C, Howell P, “Classification of Types of Stuttering Symptoms Based on Brain Activity”, PLoS ONE, e39747. doi:10.1371/journal.pone.0039747,2012

    [5] Arghavan Bahadorinejad, Farshad Almasganj, “ Delayed Auditory Feedback for Speech Disorders”, International Conference on Biomedical Engineering, 978- 1-4577-2, 2011.

    [6] Marius Cristian, Adrian Graur, “Developing a Logopaedic Mobile Device Using FPGA”, Applied Computational Intelligence and Informatics, 1-4244-1234- X, 2007

    [7] Walter Dosch, Nontasak Jacchum, “ Stuttering RemovalDeveloping Mealy and Moore Style Implementations of an Interactive Component”, Computer Systems and Applications, ISBN 978-1-4244-3807-5, pp. 302-308, 2009

    [8] Juray Palfy, Jirt Pospichal, “ Pattern Search in Disfluent Speech”, IEEE International Workshop on Machoine Learning for Signal Processing, 2012

    [9] K.M Ravikumar, R.Rajagopal, H.C.Nagaraj “An Approach for Objective Assessment of Stuttered Speech Using MFCC Features” ICGST, DSP Journal, Volume 9, Issue 1, June, 2009 pp. 19-24, june, 2009.

    [10] W. reichl and G. Ruske, “ Syllable Segmentation of Continuous Speech with Artificial Neural Networks,” In processing of Eurospeech, Berlin, Vol.3,pp.1771-1774,1993.

    [11] P.Howell, S. Sackin and K. Glenn,”Development of a two stage procedure for the automatic recognition of disfluencies in the speech of children who stutter: II. ANN recognition of repetitions and prolongations with supplied word segment markers,” Journal of speech Language and Hearing Research, Vol 40, pp. 1085, 1997

    [12] Y.V. Geetha, K. Pratibha, R.Ashok, and S.K.Ravindra” Classification of childhood disfluencies using neural networks” Journal of Fluency disorders, vol.25, pp.99-117, 2000.

    [13] Coneliu Octavian, “A Comparative Study of Feature Extraction Methods Applied to Continous Speech Recognition in Romanian Language”, 48th International Symposium ELMAR-2006, 07-09 june 2006,


Recent Article