Voice translator based on natural language processing to assist children and young people with dyslalia

Authors

DOI:

https://doi.org/10.70929/caui3.v1i2.0012

Keywords:

Dislalia, voice recognition, natural language processing, speech therapy

Abstract

The voice translator attempts to correct dyslalia in children and young people, using advanced natural language processing technologies. Procedures such as the selection of advanced tools (Vosk, Google Speech-to-Text, and OpenAI Whisper) and the design of an intuitive interface were implemented to ensure the functionality of the prototype. Iterative testing was conducted to validate the system's performance and gather feedback from therapists and educators. The results showed that the system achieved an average accuracy of 90% in speech recognition, meeting established standards. In addition, certain areas for improvement were identified, such as the detection of complex phonemes (/r/ and /s/), where higher error rates were recorded. It is concluded that the system has a significant impact in the educational and therapeutic fields.

Author Biographies

  • Luis González-Franco, Faculty of Industrial Engineering, University of Guayaquil, Guayaquil 090514, Ecuador

    Luis González Franco holds a degree in Industrial Engineering from the Universidad de Guayaquil.

  • James Sánchez-Calderón, Faculty of Industrial Engineering, Universidad de Guayaquil, Guayaquil 090514, Ecuador

    James Sánchez Calderón holds a degree in Industrial Engineering from the Universidad de Guayaquil.

References

[1] E. López-Hernández, P. Acosta-Rodas, J. Cruz-Cárdenas, and C. Ramos-Galarza, “Intervención musicoterapéutica para mejorar la memoria, atención y lenguaje in niños con dislalia.,” Revista Ecuatoriana de Neurologia, vol. 30, no. 2, pp. 48–56, Sep. 2021, doi: 10.46997/revecuatneurol30200048.

[2] N. R. Garofalo Cujilema and A. Y. Morán Melendez, “Bullying y estado emocional en estudiantes de sexto grado de Educación General Básica de la Unidad Educativa 24 de Mayo del cantón San Miguel de Bolívar,” BABAHOYO: UTB, 2024, 2024.

[3] M. I. Mendoza Loor and L. E. Loor Lino, “Labor de trabajador social frente al trabajo infantil de los niños, niñas y adolescentes en el cantón Portoviejo,” AlfaPublicaciones, vol. 3, no. 4, pp. 6–19, Oct. 2021, doi: 10.33262/ap.v3i4.106.

[4] N. E. G. Rivas, “Tecnolog’ia Asistiva para la Inclusión Educativa en Ecuador,” Ciencia Latina: Revista Multidisciplinar, vol. 8, no. 3, pp. 417–433, 2024.

[5] C. Bérubé et al., “Voice-Based Conversational Agents for the Prevention and Management of Chronic and Mental Health Conditions: Systematic Literature Review,” J Med Internet Res, vol. 23, no. 3, p. e25933, Mar. 2021, doi: 10.2196/25933.

[6] K. Lister, T. Coughlan, F. Iniesto, N. Freear, and P. Devine, “Accessible conversational user interfaces,” in Proceedings of the 17th International Web for All Conference, New York, NY, USA: ACM, Apr. 2020, pp. 1–11. doi: 10.1145/3371300.3383343.

[7] F. Khan, Y. Wu, J. Dray, B. Hemsley, and A. B. Kocaballi, “Conversational Agents to Support People with Communication Disability: A Co-design Study with Speech Pathologists,” in Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems, New York, NY, USA: ACM, Apr. 2025, pp. 1–9. doi: 10.1145/3706599.3719800.

[8] F. J. Espinoza-Santacruz and C. H. Flores-Urgiles, “Aplicación de tecnologías de la información en el desarrollo del lenguaje de niños con dificultades de comunicación,” Polo del Conocimiento, vol. 4, no. 5, p. 116, May 2019, doi: 10.23857/pc.v4i5.968.

[9] N. E. Garcia Rivas, “Tecnología Asistiva para la Inclusión Educativa en Ecuador,” Ciencia Latina Revista Científica Multidisciplinar, vol. 8, no. 3, pp. 417–433, May 2024, doi: 10.37811/cl_rcm.v8i3.11228.

[10] B. Roy, S. Ghosh, S. K. Sarkar, A. Sen, and N. R. Choudhury, “Implications of Artificial Intelligence for Special Education Technology,” 2024, pp. 401–430. doi: 10.4018/979-8-3693-5538-1.ch015.

[11] M. Mahmoudi-Dehaki and N. Nasr-Esfahani, “Artificial Intelligence (AI) in Special Education,” 2024, pp. 193–222. doi: 10.4018/979-8-3693-5538-1.ch007.

[12] X. Vélez-Calvo, V. Calle-Calle, C. Seade-Mejía, and M. J. Peñaherrera-Vélez, “Doble excepcionalidad: altas capacidades y trastornos del neurodesarrollo. prevalencia en escolares ecuatorianos,” CienciAmérica, vol. 12, no. 1, Jan. 2023, doi: 10.33210/ca.v12i1.393.

[13] G. A. Attwell, K. E. Bennin, and B. Tekinerdogan, “A Systematic Review of Online Speech Therapy Systems for Intervention in Childhood Speech Communication Disorders,” Sensors, vol. 22, no. 24, p. 9713, Dec. 2022, doi: 10.3390/s22249713.

[14] Z. Brahmi, M. Mahyoob, M. Al-Sarem, J. Algaraady, K. Bousselmi, and A. Alblwi, “Exploring the Role of Machine Learning in Diagnosing and Treating Speech Disorders: A Systematic Literature Review,” Psychol Res Behav Manag, vol. Volume 17, pp. 2205–2232, May 2024, doi: 10.2147/PRBM.S460283.

[15] K. I. Arce-Ruelas, O. Alvarez-Xochihua, J. A. Gonzalez-Fraga, E. Martinez-Martinez, and P. Paez-Manjarrez, “Design and Evaluation of a Spanish Language Therapy Support System,” Journal of Language Teaching and Research, vol. 12, no. 6, pp. 853–863, Nov. 2021, doi: 10.17507/jltr.1206.01.

[16] J. Vonessen, N. B. Aoki, M. Cohn, and G. Zellou, “Comparing perception of L1 and L2 English by human listeners and machines: Effect of interlocutor adaptations,” J Acoust Soc Am, vol. 155, no. 5, pp. 3060–3070, May 2024, doi: 10.1121/10.0025930.

[17] Q. Yang, “Toward Responsible AI: An Overview of Federated Learning for User-centered Privacy-preserving Computing,” ACM Trans Interact Intell Syst, vol. 11, no. 3–4, pp. 1–22, Dec. 2021, doi: 10.1145/3485875.

[18] D. Jiang et al., “A GDPR-compliant Ecosystem for Speech Recognition with Transfer, Federated, and Evolutionary Learning,” ACM Trans Intell Syst Technol, vol. 12, no. 3, pp. 1–19, Jun. 2021, doi: 10.1145/3447687.

[19] R. Lakshminarayanan, A. Shaik, and A. Balasundaram, “Automated speech therapy through personalized pronunciation correction using reinforcement learning and large language models,” Results in Engineering, vol. 25, p. 103943, Mar. 2025, doi: 10.1016/j.rineng.2025.103943.

[20] C. Song, S.-Y. Shin, and K.-S. Shin, “Optimizing Foreign Language Learning in Virtual Reality: A Comprehensive Theoretical Framework Based on Constructivism and Cognitive Load Theory (VR-CCL),” Applied Sciences, vol. 13, no. 23, p. 12557, Nov. 2023, doi: 10.3390/app132312557.

[21] G. A. Ikhimwin, “Dynamic Interactive Multimodal Speech (DIMS) Framework,” Frontiers in Global Health Sciences, pp. 1–13, Jan. 2023, doi: 10.70560/1s1ky152.

Downloads

Published

2025-08-13

Issue

Vol. 1 No. 2 (2025): Ciencia al Servicio de la Sociedad

Section

Research Paper

Categories

License

Copyright (c) 2025 Scientific Digital Journal Causality Causality (caui3)

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
L. González-Franco and J. Sánchez-Calderón, “Voice translator based on natural language processing to assist children and young people with dyslalia”, Revista Digital Científica Causalidad (caui3), vol. 1, no. 2, pp. 15–25, Aug. 2025, doi: 10.70929/caui3.v1i2.0012.