Detecting Stuttering Events in Transcripts of Children’s Speech

  • Sadeen AlharbiEmail author
  • Madina Hasan
  • Anthony J. H. Simons
  • Shelagh Brumfitt
  • Phil Green
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10583)


Stuttering is a common problem in childhood that may persist into adulthood if not treated in early stages. Techniques from spoken language understanding may be applied to provide automated diagnosis of stuttering from children speech. The main challenges however lie in the lack of training data and the high dimensionality of this data. This study investigates the applicability of machine learning approaches for detecting stuttering events in transcripts. Two machine learning approaches were applied, namely HELM and CRF. The performance of these two approaches are compared, and the effect of data augmentation is examined in both approaches. Experimental results show that CRF outperforms HELM by 2.2% in the baseline experiments. Data augmentation helps improve systems performance, especially for rarely available events. In addition to the annotated augmented data, this study also adds annotated human transcriptions from real stuttered children’s speech to help expand the research in this field.


Stuttering event detection Speech disorder Human-computer interaction CRF HELM 



This research has been supported by the Saudi Ministry of Education, King Saud University.


  1. 1.
    Brundage, S.B., Bothe, A.K., Lengeling, A.N., Evans, J.J.: Comparing judgments of stuttering made by students, clinicians, and highly experienced judges. J. Fluen. Dis. 31(4), 271–283 (2006)CrossRefGoogle Scholar
  2. 2.
    Craig, A., Calver, P.: Following up on treated stutterers studies of perceptions of fluency and job status. J. Speech Lang. Hear. Res. 34(2), 279–284 (1991)CrossRefGoogle Scholar
  3. 3.
    Geetha, Y., Pratibha, K., Ashok, R., Ravindra, S.K.: Classification of childhood disfluencies using neural networks. J. Fluen. Dis. 25(2), 99–117 (2000)CrossRefGoogle Scholar
  4. 4.
    Gregory, H.H., Campbell, J.H., Gregory, C.B., Hill, D.G.: Stuttering Therapy: Rationale and Procedures. Allyn & Bacon, Boston (2003)Google Scholar
  5. 5.
    Hayhow, R., Cray, A.M., Enderby, P.: Stammering and therapy views of people who stammer. J. Fluen. Dis. 27(1), 1–17 (2002)CrossRefGoogle Scholar
  6. 6.
    Heeman, P.A., Lunsford, R., McMillin, A., Yaruss, J.S.: Using clinician annotations to improve automatic speech recognition of stuttered speech. In: Interspeech 2016, pp. 2651–2655 (2016)Google Scholar
  7. 7.
    Heeman, P.A., McMillin, A., Yaruss, J.S.: Computer-assisted disfluency counts for stuttered speech. In: INTERSPEECH, pp. 3013–3016 (2011)Google Scholar
  8. 8.
    Howell, P., Davis, S., Bartrip, J.: The university college London archive of stuttered speech (uclass). J. Speech Lang. Hear. Res. 52(2), 556–569 (2009)CrossRefGoogle Scholar
  9. 9.
    Howell, P., Sackin, S.: Automatic recognition of repetitions and prolongations in stuttered speech. In: Proceedings of the first World Congress on fluency disorders, vol. 2, pp. 372–374 (1995)Google Scholar
  10. 10.
    Jaitly, N., Hinton, G.E.: Vocal tract length perturbation (VTLP) improves speech recognition. In: Proceeding ICML Workshop on Deep Learning for Audio, Speech and Language (2013)Google Scholar
  11. 11.
    Jones, M., Onslow, M., Packman, A., Williams, S., Ormond, T., Schwarz, I., Gebski, V.: Randomised controlled trial of the lidcombe programme of early stuttering intervention. BMJ 331(7518), 659 (2005). CrossRefGoogle Scholar
  12. 12.
    Kudoh, T.: CRF++ (2007).
  13. 13.
    Liao, H., Pundak, G., Siohan, O., Carroll, M., Coccaro, N., Jiang, Q.M., Sainath, T.N., Senior, A., Beaufays, F., Bacchiani, M.: Large vocabulary automatic speech recognition for children. In: Interspeech (2015)Google Scholar
  14. 14.
    Liu, H., Gegov, A., Cocea, M.: Complexity control in rule based models for classification in machine learning context. In: Angelov, P., Gegov, A., Jayne, C., Shen, Q. (eds.) Advances in Computational Intelligence Systems. AISC, vol. 513, pp. 125–143. Springer, Cham (2017). doi: 10.1007/978-3-319-46562-3_9 CrossRefGoogle Scholar
  15. 15.
    Mahesha, P., Vinod, D.S.: Using orthographic transcripts for stuttering dysfluency recognition and severity estimation. In: Jain, L.C., Patnaik, S., Ichalkaranje, N. (eds.) Intelligent Computing, Communication and Devices. AISC, vol. 308, pp. 613–621. Springer, New Delhi (2015). doi: 10.1007/978-81-322-2012-1_66 CrossRefGoogle Scholar
  16. 16.
    Juste, F.S., de Andrade, C.R.F.: Speech disfluency types of fluent and stuttering individuals: age effects. Folia Phoniatr. et Logop. 63(2), 57–64 (2010)CrossRefGoogle Scholar
  17. 17.
    Stolcke, A., Shriberg, E.: Statistical language modeling for speech disfluencies. In: 1996 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP-1996, vol. 1, pp. 405–408. IEEE (1996)Google Scholar
  18. 18.
    Stolcke, A., et al.: SRILM-an extensible language modeling toolkit. In: Interspeech, pp. 901–904 (2002)Google Scholar
  19. 19.
    Tseng, H., Chang, P., Andrew, G., Jurafsky, D., Manning, C.: A conditional random field word segmenter for sighan bakeoff 2005. In: Proceedings of the Fourth SIGHAN Workshop on Chinese Language Processing, vol. 171. Citeseer (2005)Google Scholar
  20. 20.
    Vertanen, K.: Csr lm-1 language model training recipe (2007)Google Scholar
  21. 21.
    Yairi, E., Ambrose, N.G.: Early childhood stuttering ipersistency and recovery rates. J. Speech Lang. Hear. Res. 42(5), 1097–1112 (1999)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Sadeen Alharbi
    • 1
    Email author
  • Madina Hasan
    • 1
  • Anthony J. H. Simons
    • 1
  • Shelagh Brumfitt
    • 2
  • Phil Green
    • 1
  1. 1.Department of Computer ScienceThe University of SheffieldSheffieldUK
  2. 2.Department of Human Communication SciencesThe University of SheffieldSheffieldUK

Personalised recommendations