Using Artificial Intelligence for sign language translation: a systematic literature review

Abstract

Introduction: in this systematic literature review, the use of artificial intelligence in sign language translation for people with hearing and speech loss was analyzed. This review aims to identify the results of the application of artificial intelligence to sign language translation. Method: 462 articles, original and conference papers in SCOPUS, until June 2023, and relying on a selection process based on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement, of which 26 studies met exclusion and inclusion criteria. Convolutional Neural Network (CNN) was the most widely implemented machine learning technique in the selected studies. Results: Many sign language systems were tested with various artificial intelligence algorithms and datasets on different continents to create new models and improve sign language translation accuracy. An increasing use of neural networks to achieve better sign language translation efficiency was identified, achieving results ranging from 90 % to 100 % accuracy. Conclusions: The application of artificial intelligence has greatly excelled in the field of Computer Science and has significantly improved the accuracy of sign language translation which has led to lower communication barriers between natural persons and persons with communication disabilities.

Contribution of graph theory to the understanding of social dynamics

“…Los criterios de inclusión se centraron en la identificación adecuada de los artículos más relevantes de los últimos cinco años (2018-2023), en idioma inglés, publicados por editoriales de prestigio (Elsevier, Taylor & Francis, Emerald), que ofrecieran datos empíricos o analíticos resultantes de la revisión de la literatura. En cambio, los criterios de exclusión permitieron eliminar estudios no relevantes, enfocados a categorías auxiliares o que no desarrollase la teoría de grafos, duplicados, entre otros (Bacsu et al, 2021;Hung et al, 2020;Ortiz-Leon et al, 2023;Sonke et al, 2021).…”