Large Sign Language Models: Toward 3D American Sign Language Translation

TL;DR

This paper introduces Large Sign Language Models (LSLM) that translate 3D American Sign Language directly from spatial data, significantly improving accuracy and inclusivity in digital communication for the hearing-impaired.

Contribution

It presents a novel framework leveraging 3D data and large language models for ASL translation, moving beyond 2D video-based methods and enabling multimodal language understanding.

Findings

Enhanced translation accuracy from 3D sign data

Flexible translation via instruction-guided prompts

Foundation for multimodal language processing

Abstract

We present Large Sign Language Models (LSLM), a novel framework for translating 3D American Sign Language (ASL) by leveraging Large Language Models (LLMs) as the backbone, which can benefit hearing-impaired individuals' virtual communication. Unlike existing sign language recognition methods that rely on 2D video, our approach directly utilizes 3D sign language data to capture rich spatial, gestural, and depth information in 3D scenes. This enables more accurate and resilient translation, enhancing digital communication accessibility for the hearing-impaired community. Beyond the task of ASL translation, our work explores the integration of complex, embodied multimodal languages into the processing capabilities of LLMs, moving beyond purely text-based inputs to broaden their understanding of human communication. We investigate both direct translation from 3D gesture features to text and an instruction-guided setting where translations can be modulated by external prompts, offering greater flexibility. This work provides a foundational step toward inclusive, multimodal intelligent systems capable of understanding diverse forms of language.