Using neural networks to correct speech defects in children.

Keywords: language, speech defects, sounds, convolutional neural network.


Determination of speech defects in a child is an urgent scientific and practical task, since timely correction of speech can improve the child's communication skills in the future. Based on the analysis given in the work, it is logical to use convolutional neural networks as a tool to identify a defect and its type. The work is devoted to the development of an algorithm for the identified speech defect, which includes the preparation of data for training the model and the use of a convolutional neural network that was developed. The architecture of a convolutional neural network is described. Experiments were carried out to verify the accuracy and adequacy of the developed neural network model, the results are presented in the form of tabular data.


Survey on deep neural networks in speech and vision systems. M Alam, MD Samad, L Vidyaratne, A Glandon, KM Iftekharuddin. Neurocomputing 417, 302-321, 2020.

Deep Representation Learning in Speech Processing: Challenges, Recent Advances, and Future Trends. Siddique Latif1, Rajib Rana, Sara Khalifa, 2020, 25 pages.

Hendrik Purwins, Bo Li, Tuomas Virtanen, Jan Schlüter, Shuoyiin Chang, Tara Sainath. Deep Learning for Audio Signal Processing. In Journal of Selected Topics of Signal Processing, Vol. 13, No. 2, May 2019, pages 206–219.

Automated speech-based screening of depression using deep convolutional neural networks. Karol Chlastaa,b, Krzysztof Wołka, Izabela Krejtz, 2019, 11 pages.

Shakeel A. Sheikh, Md Sahidullah, Fabrice Hirsch, and Slim Ouni. 2021. Machine Learning for Stuttering Identification: Review, Challenges & Future Directions. under review in ACM Comput. Surv. 54, 4 (July 2021), 27 pages.

FluentNet: End-to-End Detection of Speech Disfluency with Deep Learning. Tedd Kourkounakis, Amirhossein Hajavi, and Ali Etemad, 2020, 13 pages.

Music Genre Classification using Masked Conditional Neural Networks. Fady Medhat, David Chesmore, and John Robinson, 2018, 11 pages.

Supervised Speech Separation Based on Deep Learning: An Overview. DeLiang Wang, Fellow, IEEE, Jitong Chen, 2018, 27 pages.

Matveyeav N. Chynnyky vplyvu na movlennyevi porushennya ditey molodshoho shkilʹnoho viku / N. Matveyeva // Osvitniy prostir Ukrayiny, 2019, 159 s.

S.Haykin. Neural Networks and Learning Machines. 3rd Edition. Pearson, 2018.

Abstract views: 0
PDF Downloads: 0
How to Cite
Pronina , O., & Dehtiar , V. (2021). Using neural networks to correct speech defects in children . COMPUTER-INTEGRATED TECHNOLOGIES: EDUCATION, SCIENCE, PRODUCTION, (44), 127-133.
Computer science and computer engineering