Towards Online Continuous Sign Language Recognition and Translation

Ronglai Zuo, Fangyun Wei, Brian Mak


Abstract
Research on continuous sign language recognition (CSLR) is essential to bridge the communication gap between deaf and hearing individuals. Numerous previous studies have trained their models using the connectionist temporal classification (CTC) loss. During inference, these CTC-based models generally require the entire sign video as input to make predictions, a process known as offline recognition, which suffers from high latency and substantial memory usage. In this work, we take the first step towards online CSLR. Our approach consists of three phases: 1) developing a sign dictionary; 2) training an isolated sign language recognition model on the dictionary; and 3) employing a sliding window approach on the input sign sequence, feeding each sign clip to the optimized model for online recognition. Additionally, our online recognition model can be extended to support online translation by integrating a gloss-to-text network and can enhance the performance of any offline model. With these extensions, our online approach achieves new state-of-the-art performance on three popular benchmarks across various task settings. Code and models are available at https://github.com/FangyunWei/SLRT.
Anthology ID:
2024.emnlp-main.619
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
11050–11067
Language:
URL:
https://aclanthology.org/2024.emnlp-main.619
DOI:
Bibkey:
Cite (ACL):
Ronglai Zuo, Fangyun Wei, and Brian Mak. 2024. Towards Online Continuous Sign Language Recognition and Translation. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 11050–11067, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Towards Online Continuous Sign Language Recognition and Translation (Zuo et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.619.pdf
Software:
 2024.emnlp-main.619.software.zip