"SAWAN" A Sinhala Sign Language Generation System Using HamNoSys and SiGML

View at publisher Summarise with VIRAT
Authors: Sanuri Himalka, Udaya Wijenayake, Ravinath Wanniarachchi, Maleesha Hirushan, Pasindu Ranasinghe
Cited by: 0
References: 8

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

This study addresses the communication gap between the deaf and hearing communities through the development of a cross-platform software solution. It introduces a Sinhala Sign Language (SSL) generator supported by auxiliary tools to reduce communication barriers. The proposed system, SAWAN – Deaf Supportive Solutions, integrates editable datasets, an interactive learning platform, a static sign translator, and HamNoSys-based tools. HamNoSys, introduced to Sri Lanka for the first time through this research, provides a standardized framework for gesture representation, facilitating dataset modification and future research. The system also includes an SSL dataset built using HamNoSys and SiGML. Experimental evaluation with SSL experts yielded an average translation accuracy of 80.67%, defined through a rubric assessing correctness, fluency, and comprehensibility. Although based on a limited proof-of-concept dataset, the results demonstrate the feasibility of HamNoSys-based SSL generation and form a foundation for future improvements.

Fields of Study & Subjects

Hand Gesture Recognition Systems Hearing Impairment and Communication Natural Language Processing Techniques

Publication details

Journal / source
IEEE International Conference on Industrial and Information Systems (ICIIS)
Pages
156–161
Publication date
16 January 2026
Language
EN