Abstract
Speech disfluencies in spontaneous speech are valuable cues indicating language planning and speech execution problems in bi-lingual children during the secondary-language acquisition phase which is often confused with stuttering disfluencies. In this work, unique speech features are evaluated to set clinical benchmarks towards distinguishing linguistic impairment from stuttering disorder in bilingual Tamil-English (TE) speaking children whose primary language is Tamil (L1) and their secondary-acquired language (L2) is English. Acoustic and prosodic speech features extracted from disfluent segments of speech in the self-annotated disfluent speech corpus reveal divergence in spectral energy, pitch, formants and speech rate in Children with Stuttering Disorder (CSD) compared amid the Children with Language Impairment (CLI). The speech feature-based classification of CSD from CLI was verified with the implementation of linear and non-linear Support Vector Machine (SVM) models. The execution of the classifying models was evaluated based on their classification accuracy, F1-score, time complexities in discriminating CLI from CSD. The non-linear SVM was observed to exhibit the best classification accuracy and F1-score when the ‘polynomial’ kernel was chosen though its time complexity was higher than the linear SVM.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Howell, P., Davis, S.R., Williams, R.: The effects of bilingualism on stuttering during late childhood. Arch. Dis. Child. 94(1), 42–46 (2009)
Howell, P., Lu, C.: Assessing risk for stuttering in children. J. Fluency Disor. 38(1), 63–65 (2013)
Watson, J., Byrd, C.T., Carlo, E.: Effects of length, complexity, and grammatical correctness on stuttering in Spanish-speaking preschool children. Am. J. Speech Lang. Pathol. 20(1), 209–220 (2011)
Wang, H., Van Heuven, V.J.: Acoustical analysis of English vowels produced by Chinese, Dutch and American speakers. Linguist. Neth. 23(1), 237–248 (2006)
Mahesha, P., Vinod, D.S.: Automatic segmentation and classification of dysfluencies in stuttering speech. In: Proceedings of the Second International Conference on Information and Communication Technology for Competitive Strategies, pp. 1–6 (2016)
Pravin, S.C., Palanivelan, M.: Analysis of liguistic disfluencies in billigual children’s discourse. Int. J. Cogn. Lang. Sci. 12(6), 710–714 (2018)
Kourkounakis, T., Hajavi, A., Etemad, A.: Fluentnet: End-to-end detection of speech disfluency with deep learning (2020). arXiv preprint arXiv:2009.11394
Kourkounakis, T., Hajavi, A., Etemad, A.: Detecting multiple speech disfluencies using a deep residual network with bidirectional long short-term memory. In: Proceedings of IEEE International Conference on Prosodics, Speech and Signal Processing (ICASSP), pp. 6089–609, Barcelona, Spain (2020)
Boersma, P., Weenink, D.: Praat: Doing phonetics by computer [Computer program]. Version 5.3.51. https://www.praat.org/. Accessed 20 July 2020
Van Borsel, J., Maes, E., Foulon, S.: Stuttering and bilingualism-a review. J. Fluency Disor. 26(1), 179–206 (2001)
Orozco-Arroyave, J.R., Vásquez-Correa, J.C., et al.: NeuroSpeech: an open-source software for Parkinson’s speech analysis. Digit. Speech Process. 77(1), 207–221 (2018)
SciPy. https://www.scipy.org/. Accessed Aug 2020
Pedregosa, F., Varoquaux, G., Gramfort, A., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. 12(1), 2825–2830 (2012)
Shenker, R.C.: Multilingual children who stutter: clinical issues. J. Fluency Disor. 36(3), 186–193 (2011)
Support Vector Machines. https://scikit-learn.org/stable/modules/svm.html. Accessed 5 Oct 2020
Acknowledgment
This project is partly aided by AICTE, India (Research Progress Scheme - Grant Ref. No. 8–40/RIFD/RPS/Policy-1/2017–18) 15th March 2019. The Authors are the Investigators of the project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Ethics declarations
The authors declare no conflict of interest.
Rights and permissions
Copyright information
© 2021 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Pravin, S.C., Palanivelan, M. (2021). Acousto-Prosodic Delineation and Classification of Speech Disfluencies in Bilingual Children. In: Abraham, A., et al. Proceedings of the 12th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2020). SoCPaR 2020. Advances in Intelligent Systems and Computing, vol 1383. Springer, Cham. https://doi.org/10.1007/978-3-030-73689-7_59
Download citation
DOI: https://doi.org/10.1007/978-3-030-73689-7_59
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-73688-0
Online ISBN: 978-3-030-73689-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)