Voice-to-sign language translation using deep learning for people with hearing impairments

Authors

DOI:

https://doi.org/10.70929/caui3.v1i2.0016

Keywords:

Sign language, Deep learning, Python, MakeHuman

Abstract

The paper addresses the historical challenges faced by people with disabilities, focusing on hearing impairment and the importance of sign language. It proposes the development of a voice-to-sign language translation system using advanced technologies such as deep learning algorithms. The goal is to improve communication and accessibility for people with hearing disabilities, especially in environments where spoken language predominates. It highlights the problem of effective communication in Ecuador, both in educational and work contexts. This approach encompasses the creation and movement of an avatar, voice-to-text conversion using deep learning technologies, and the use of a sign language dictionary through a sequence of images. Finally, to evaluate the work, a sample of 50 people was tested and evaluated, demonstrating high effectiveness in translation, highlighting the accuracy of artificial intelligence, the viability on low-resource computers, and the diversity of applicable technologies.

Keywords: Sign language, Deep learning, Python, IBM Watson

Author Biography

  • Jorge Roberto Alvarado Cadena, Instituto Superior Tecnológico Carlos Cisneros

    Electronic Engineer with experience in design, implementation and supervision of residential and industrial electrical installations. Has a Master's degree in Renewable Energy and Energy Efficiency, which reinforces his ability to integrate sustainable and efficient solutions in electrical projects. In addition, he has worked as a systems developer, optimizing processes through technology, and as a NOC engineer in telephony infrastructure, managing critical networks and ensuring operational continuity in telecommunications. With teaching experience in third level studies implementing innovative methodologies such as project-based learning to create dynamic and student-centered learning environments.

References

[1] A. Franco-Segovia, “La lengua de señas ecuatoriana para la inclusión de los estudiantes con discapacidad auditiva,” Polo del Conocimiento, vol. 8, no. 2, pp. 458–469, Dec. 2023, doi: 10.23857/pc.v8i2.

[2] J. C. García, “LA DISCAPACIDAD AUDITIVA. PRINCIPALES MODELOS Y AYUDAS TÉCNICAS PARA LA INTERVENCIÓN.,” Revista Internacional de Apoyo a la Inclusión, Logopedia, Sociedad y Multiculturalidad, pp. 24–36, Dec. 2015, [Online]. Available: http://riai.jimdo.com/

[3] E. M. Ferrero, “Legal language as a barrier to access to justicefor people with disabilities,” Perspectivas, vol. 11, no. 2, pp. 3–16, Jul. 2021, doi: 10.19137/perspectivas-2021-v11n2a01.

[4] G. M. Campos, “La discapacidad en el lenguaje o el lenguaje para la discapacidad,” Diá-logos, pp. 78–89, Dec. 2021, doi: 10.5377/dialogos.v23i1.14756.

[5] M. De La Hoz Vásquez, “Barreras en la comprensión lectora en estudiantes con discapacidad auditiva en Educación Superior,” vol. 33, no. 26, pp. 77–97, Apr. 2025.

[6] D. Marín, “Desarrollo de la competencia lectora en alumnado con discapacidad auditiva: una revisión bibliográfica,” ReiDoCrea: Revista electrónica de investigación Docencia Creativa, vol. 8, pp. 142–153, Oct. 2019, doi: 10.30827/Digibug.57749.

[7] J. D. Guerrero-Balaguera and W. J. Pérez-Holguín, “Sistema traductor de la lengua de señas Colombiana a texto basado en FPGA,” DYNA (Colombia), vol. 82, no. 189, pp. 172–181, 2015, doi: 10.15446/dyna.v82n189.43075.

[8] D. Quinta Lipe and P. J. Guerrero, “Traducción inteligente de lenguaje de señas mediante aprendizaje automático y visión artificial,” Revista Criterio, vol. 5, no. 8, pp. 22–43, Apr. 2025, doi: 10.62319/criterio.v.5i8.33.

[9] M. Carguacundo and P. Constante, “Traductor de texto y voz a lengua de señas ecuatoriana a través de un avatar implementado para dispositivos Android,” Infociencia, vol. 12, no. 1, pp. 20–25, 2018.

[10] E. E. P. Gonzalez and C. R. I. Chamorro, “Desarrollo e implementación de un sistema que permita la accesibilidad de los servicios a personas con discapacidad auditiva/sordos (PcDa/Sordos) por medio de un aplicativo intérprete a lengua de señas en tiempo real,” in Anais do XVIII Congresso Latino-Americano de Software Livre e Tecnologias Abertas (Latinoware 2021), Sociedade Brasileira de Computação - SBC, Oct. 2021, pp. 154–157. doi: 10.5753/latinoware.2021.19924.

[11] D. L. C. Peleo, M. M. Patalay, J. M. Dela Cruz, and E. A. Ramirez, “Sign the Voice: An Embedded Software for Voice to Sign Language Translation,” in 2024 2nd International Conference on Computing and Data Analytics (ICCDA), IEEE, Nov. 2024, pp. 1–6. doi: 10.1109/ICCDA64887.2024.10867405.

[12] I. M. Greca, J. Ortiz-Revilla, and I. Arriassecq, “Diseño y evaluación de una secuencia de enseñanza-aprendizaje STEAM para Educación Primaria,” Revista Eureka sobre Enseñanza y Divulgación de las Ciencias, vol. 18, no. 1, pp. 1–20, 2021, doi: 10.25267/Rev_Eureka_ensen_divulg_cienc.2021.v18.i1.1802.

[13] Á. López-Mota and G. Moreno-Arcuri, “SUSTENTACIÓN TEÓRICA Y DESCRIPCIÓN METODOLÓGICA DEL PROCESO DE OBTENCIÓN DE CRITERIOS DE DISEÑO Y VALIDACIÓN PARA SECUENCIAS DIDÁCTICAS BASADAS EN MODELOS: EL CASO DEL FENÓMENO DE FERMENTACIÓN.,” Revista Bio-grafía Escritos sobre la biología y su enseñanza, vol. 7, no. 13, p. 109, Dec. 2014, doi: 10.17227/20271034.vol.7num.13bio-grafia109.126.

[14] C. Arana, “Redes neuronales recurrentes: Análisis de los modelos especializados en datos secuenciales,” May 2021. [Online]. Available: www.cema.edu.ar/publicaciones/doc_trabajo.html

[15] H. Lyu, N. Sha, S. Qin, M. Yan, Y. Xie, and R. Wang, “Manifold Denoising by Nonlinear Robust Principal Component Analysis.”

[16] M. van Gerven and S. Bohte, “Editorial: Artificial Neural Networks as Models of Neural Information Processing,” Front Comput Neurosci, vol. 11, Dec. 2017, doi: 10.3389/fncom.2017.00114.

[17] Consejo Nacional de Igualdad de Discapacidades (CONADIS), “Diccionario de Lengua de Señas Ecuatoriana Gabriel Román,” http://www.plataformaconadis.gob.ec/~platafor/diccionario/.

Downloads

Published

2025-12-18

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]
J. R. Alvarado Cadena, “Voice-to-sign language translation using deep learning for people with hearing impairments”, Revista Digital Científica Causalidad (caui3), vol. 1, no. 2, pp. 46–56, Dec. 2025, doi: 10.70929/caui3.v1i2.0016.