Fingerspelling, the manual representation of alphabetic characters, is a core element of sign languages. Learners report that reading back fingerspelling is among the most challenging aspects of learning sign languages, primarily due to limited practice opportunities. This paper presents AuslanSpell, a novel technology designed to enhance proficiency in Australian Sign Language (Auslan) fingerspelling. AuslanSpell allows learners to input any English word and produces 3D animated models that articulate the corresponding Auslan signs, featuring smooth hand transitions. In tests with 33 novice signers, after brief interaction with AuslanSpell, participants performed above chance on beginner multiple-choice tasks, correctly identified first and last letters more often than middle letters in free-text tasks, and reported high satisfaction – especially with features such as adjustable signing speeds and rotatable views. The results confirm AuslanSpell’s potential in enhancing the comprehension and engagement of fingerspelling learners. AuslanSpell will be available through Auslan Signbank and Apple App Store, across iOS, iPadOS, macOS, and the web.

The trend in sign language generation is centered around data-driven generative methods that require vast amounts of precise 2D and 3D human pose data to achieve an acceptable generation quality. However, currently, most sign language datasets are video-based and limited to automatically reconstructed 2D human poses (i.e., keypoints) and lack accurate 3D information. Furthermore, existing state-of-the-art for automatic 3D human pose estimation from sign language videos is prone to self-occlusion, noise, and motion blur effects, resulting in poor reconstruction quality. In response to this, we introduce DexAvatar, a novel framework to reconstruct bio-mechanically accurate fine-grained hand articulations and body movements from in-the-wild monocular sign language videos, guided by learned 3D hand and body priors. DexAvatar achieves strong performance in the SGNify motion capture dataset, the only benchmark available for this task, reaching an improvement of 35.11% in the estimation of body and hand poses compared to the state-of-the-art. The official website of this work is: https://github.com/kaustesseract/DexAvatar.