Sign Language Recognition and Translation for Low-Resource Languages: Challenges and Pathways Forward

TL;DR

This paper reviews challenges in low-resource sign language recognition, emphasizing community involvement, transfer learning, and data-centric AI, with a focus on Azerbaijani Sign Language and practical pathways forward.

Contribution

It introduces a systematic review highlighting actionable lessons, proposes paradigm shifts in AI approaches, and offers a technical roadmap for Azerbaijani Sign Language recognition.

Findings

Community co-design enhances recognition accuracy.

Transfer learning from related Turkic sign languages is effective.

A roadmap for lightweight, offline-capable AzSL recognition systems.

Abstract

Sign languages are natural, visual-gestural languages used by Deaf communities worldwide. Over 300 distinct sign languages remain severely low-resource due to limited documentation, sparse datasets, and insufficient computational tools. This systematic review synthesizes literature on sign language recognition and translation for under-resourced languages, using Azerbaijan Sign Language (AzSL) as a case study. Analysis of global initiatives extracts eight actionable lessons, including community co-design, dialectal diversity capture, and privacy-preserving pose-based representations. Turkic sign languages (Kazakh, Turkish, Azerbaijani) receive special attention, as linguistic proximity enables effective transfer learning. We propose three paradigm shifts: from architecture-centric to data-centric AI, from signer-independent to signer-adaptive systems, and from reference-based to task-specific evaluation metrics. A technical roadmap for AzSL leverages lightweight MediaPipe-based architectures, community-validated annotations, and offline-first deployment. Progress requires sustained interdisciplinary collaboration centered on Deaf communities to ensure cultural authenticity, ethical governance, and practical communication benefit.