Open-Domain Sign Language Translation Learned from Online Video
This work addresses the challenge of open-domain sign language translation for broader accessibility, though it is incremental with novel methods for known bottlenecks.
The authors tackled the problem of sign language translation in real-world settings by introducing OpenASL, a large-scale dataset with 288 hours of ASL videos from online sources, and proposed techniques that improved translation quality over baselines.
Existing work on sign language translation - that is, translation from sign language videos into sentences in a written language - has focused mainly on (1) data collected in a controlled environment or (2) data in a specific domain, which limits the applicability to real-world settings. In this paper, we introduce OpenASL, a large-scale American Sign Language (ASL) - English dataset collected from online video sites (e.g., YouTube). OpenASL contains 288 hours of ASL videos in multiple domains from over 200 signers and is the largest publicly available ASL translation dataset to date. To tackle the challenges of sign language translation in realistic settings and without glosses, we propose a set of techniques including sign search as a pretext task for pre-training and fusion of mouthing and handshape features. The proposed techniques produce consistent and large improvements in translation quality, over baseline models based on prior work. Our data and code are publicly available at https://github.com/chevalierNoir/OpenASL