Effect of Data Augmentation with Multi-View Perspectives of Signers on the DGS-Fabeln-1 Dataset

Fabian Renner, Daksitha Withanage Don, Elisabeth Andre, Cristina Luna Jimenez


Abstract
Sign languages constitute the principal form of communication for deaf communities across the globe. Nevertheless, the development of reliable Continuous Sign Language Translation (CSLT) systems is constrained by the lack of sufficient data and models able to handle spatio-temporal information. In this article, we explore the effect of adding multiview perspectives of the signer to the training set as data augmentation using the UniSign framework for the DGS-Fabeln-1 dataset. Our results reveal that increasing dataset size and using multiple camera perspectives significantly improve performance, with the best configurations achieving BLEU-4 scores of 4.20%. These results provide a competitive baseline for the DGS-Fabeln-1 dataset and guidance for further optimizations of CSLT systems.
Anthology ID:
2026.signlang-1.44
Volume:
Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Eleni Efthimiou, Stavroula-Evita Fotinea, Thomas Hanke, Julie A. Hochgesang, Johanna Mesch, Marc Schulder
Venues:
SignLang | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
429–437
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-signlang-44
DOI:
10.63317/2zrdptjrx3pa
Bibkey:
Cite (ACL):
Fabian Renner, Daksitha Withanage Don, Elisabeth Andre, and Cristina Luna Jimenez. 2026. Effect of Data Augmentation with Multi-View Perspectives of Signers on the DGS-Fabeln-1 Dataset. In Proceedings of the LREC 2026 12th Workshop on the Representation and Processing of Sign Languages: Language in Motion, pages 429–437, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Effect of Data Augmentation with Multi-View Perspectives of Signers on the DGS-Fabeln-1 Dataset (Renner et al., SignLang 2026)
Copy Citation: