Deaf signers face persistent communication barriers in healthcare settings, where reliance on third-party interpreters can compromise privacy precisely when confidentiality matters most. We present LSC-CARE, the first annotated dataset of Catalan Sign Language (LSC) for the medical domain, comprising 2,784 signed segments (approximately 4.5 hours) produced by 11 deaf native signers across ten emergency-care topics. Each segment is paired with time-aligned ID-gloss annotations produced by a deaf native linguist and written Catalan translations produced by an LSC interpreter, following conventions consistent with the LSC SignBank. To assess the dataset’s utility for Sign Language Translation, we benchmark three settings: a gloss-free end-to-end video-to-text model, a cascade of sign language recognition and gloss-to-text translation, and an oracle gloss-to-text upper bound. The cascade consistently outperforms the end-to-end approach despite a high gloss error rate, and, unlike it, is statistically invariant to signer identity, while the 21-BLEU gap between cascade and oracle identifies visual sign recognition as the main bottleneck for low-resource medical SLT. We release the dataset to support accessible healthcare technologies for the Catalan Deaf community.

This paper proposes a hybrid methodology to generate high-quality synthetic data. Unlike other approaches based purely on generative Artificial Intelligence, which may suffer from hallucinations or inconsistent movements, this project uses 3D biomechanics and kinematics algorithms that enforce the anatomical constraints of the human body to ensure physically plausible movements. The aim of this research is to demonstrate that it is possible to synthetically expand the dataset. In particular, this paper focuses on verb agreement, a grammatical domain which is known for its morphological and articulatory complexity. By concentrating on the possible configurations of the movements in signing space when expressing different person agreeing verbal forms, we aim to capture real movements to extract physical parameters and apply them as logical rules —similar to those of a video game engine— to automatically synthesize thousands of new conjugations from infinitives with complete anatomical precision. Beyond spatial conjugation, the methodology further augments data through procedural variation of prosody and body morphology.