Continuous Bangla Sign Language Translation: Mitigating the Expense of Gloss Annotation with the Assistance of Graph

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Arib, Safaeid Hossain, Akter, Rabeya, Rahman, Sejuti
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866913991653064704
author Arib, Safaeid Hossain
Akter, Rabeya
Rahman, Sejuti
author_facet Arib, Safaeid Hossain
Akter, Rabeya
Rahman, Sejuti
contents Millions of individuals worldwide are affected by deafness and hearing impairment. Sign language serves as a sophisticated means of communication for the deaf and hard of hearing. However, in societies that prioritize spoken languages, sign language often faces underestimation, leading to communication barriers and social exclusion. The Continuous Bangla Sign Language Translation project aims to address this gap by enhancing translation methods. While recent approaches leverage transformer architecture for state-of-the-art results, our method integrates graph-based methods with the transformer architecture. This fusion, combining transformer and STGCN-LSTM architectures, proves more effective in gloss-free translation. Our contributions include architectural fusion, exploring various fusion strategies, and achieving a new state-of-the-art performance on diverse sign language datasets, namely RWTH-PHOENIX-2014T, CSL-Daily, How2Sign, and BornilDB v1.0. Our approach demonstrates superior performance compared to current translation outcomes across all datasets, showcasing notable improvements of BLEU-4 scores of 4.01, 2.07, and 0.5, surpassing those of GASLT, GASLT and slt_how2sign in RWTH-PHOENIX-2014T, CSL-Daily, and How2Sign, respectively. Also, we introduce benchmarking on the BornilDB v1.0 dataset for the first time. Our method sets a benchmark for future research, emphasizing the importance of gloss-free translation to improve communication accessibility for the deaf and hard of hearing.
format Preprint
id arxiv_https___arxiv_org_abs_2508_10687
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Continuous Bangla Sign Language Translation: Mitigating the Expense of Gloss Annotation with the Assistance of Graph
Arib, Safaeid Hossain
Akter, Rabeya
Rahman, Sejuti
Computation and Language
Artificial Intelligence
Millions of individuals worldwide are affected by deafness and hearing impairment. Sign language serves as a sophisticated means of communication for the deaf and hard of hearing. However, in societies that prioritize spoken languages, sign language often faces underestimation, leading to communication barriers and social exclusion. The Continuous Bangla Sign Language Translation project aims to address this gap by enhancing translation methods. While recent approaches leverage transformer architecture for state-of-the-art results, our method integrates graph-based methods with the transformer architecture. This fusion, combining transformer and STGCN-LSTM architectures, proves more effective in gloss-free translation. Our contributions include architectural fusion, exploring various fusion strategies, and achieving a new state-of-the-art performance on diverse sign language datasets, namely RWTH-PHOENIX-2014T, CSL-Daily, How2Sign, and BornilDB v1.0. Our approach demonstrates superior performance compared to current translation outcomes across all datasets, showcasing notable improvements of BLEU-4 scores of 4.01, 2.07, and 0.5, surpassing those of GASLT, GASLT and slt_how2sign in RWTH-PHOENIX-2014T, CSL-Daily, and How2Sign, respectively. Also, we introduce benchmarking on the BornilDB v1.0 dataset for the first time. Our method sets a benchmark for future research, emphasizing the importance of gloss-free translation to improve communication accessibility for the deaf and hard of hearing.
title Continuous Bangla Sign Language Translation: Mitigating the Expense of Gloss Annotation with the Assistance of Graph
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2508.10687