Real-time sign language to speech translation using CNNs
Computer Science and Mathematical Modelling · 15.11.2026 · 0 (23/2026) · 19-27
DOI: 10.5604/01.3001.0055.9904 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer Science and Mathematical Modelling, erschienen am 15.11.2026. Verfasst von Piotr Krzysztof Gdula. Die Arbeit nennt 14 Literaturangaben.
Abstract (Originalsprache)
This article presents the design, implementation, and empirical evaluation of an end-to-end software architecture for the real-time translation of the American Sign Language (ASL) alphabet into text and synthesized speech. The proposed system leverages the OpenCV library for video ingestion and the MediaPipe framework to extract 21 precise three-dimensional topological landmarks of the human hand, effectively isolating the gesture from environmental noise. A custom Convolutional Neural Network (CNN) built in TensorFlow and Keras processes these normalized skeletal representations to classify 26 static ASL characters. The model demonstrates a robust overall classification accuracy, performing exceptionally well on open hand topologies while highlighting occlusion-based challenges in complex gestures. Operating with exceedingly low latency, the system ensures fluid real-time human-computer interaction, providing a scalable and computationally efficient foundation for accessible communication tools without the need for specialized depth-sensing hardware.
Zitieren
APA
Gdula, P. K. (2026). Real-time sign language to speech translation using CNNs. Computer Science and Mathematical Modelling, 0(23/2026), 19-27. https://doi.org/10.5604/01.3001.0055.9904
Vancouver
Gdula PK. Real-time sign language to speech translation using CNNs. Computer Science and Mathematical Modelling. 2026;0(23/2026):19-27. doi:10.5604/01.3001.0055.9904
BibTeX
@article{Gdula2026,
author = {Gdula, Piotr Krzysztof},
title = {Real-time sign language to speech translation using CNNs},
journal = {Computer Science and Mathematical Modelling},
year = {2026},
volume = {0},
number = {23/2026},
pages = {19--27},
doi = {10.5604/01.3001.0055.9904}
}
EUVIMED