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

• URL: http://arxiv.org/abs/2511.08535v1
• Date: Wed, 12 Nov 2025 02:03:36 GMT
• Title: Large Sign Language Models: Toward 3D American Sign Language Translation
• Authors: Sen Zhang, Xiaoxiao He, Di Liu, Zhaoyang Xia, Mingyu Zhao, Chaowei Tan, Vivian Li, Bo Liu, Dimitris N. Metaxas, Mubbasir Kapadia,
• Abstract summary: We present Large Sign Language Models (LSLM), a novel framework for translating 3D American Sign Language (ASL)<n>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.<n>This enables more accurate and resilient translation, enhancing digital communication accessibility for the hearing-impaired community.
• Score: 33.777693392753385
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Lost in Translation, Found in Embeddings: Sign Language Translation and Alignment [84.39962912136525]
  We develop a model for sign language understanding that performs sign language translation (SLT) and sign-subtitle alignment (SSA)<n>Our approach is built upon three components: (i) a lightweight visual backbone that captures manual and non-manual cues from human keypoints and lip-region images; (ii) a Sliding Perceiver mapping network that aggregates consecutive visual features into word-level embeddings; and (iii) a multi-task scalable training strategy that jointly optimises SLT and SSA.
  arXiv  Detail & Related papers  (2025-12-08T21:05:46Z)
• Improving Language and Modality Transfer in Translation by Character-level Modeling [14.145120349133007]
  Current translation systems, despite being highly multilingual, cover only 5% of the world's languages.<n>We propose a character-based approach to improve adaptability to new languages and modalities.
  arXiv  Detail & Related papers  (2025-05-30T13:16:08Z)
• Real-Time Multilingual Sign Language Processing [4.626189039960495]
  Sign Language Processing (SLP) is an interdisciplinary field comprised of Natural Language Processing (NLP) and Computer Vision.<n>Traditional approaches have often been constrained by the use of gloss-based systems that are both language-specific and inadequate for capturing the multidimensional nature of sign language.<n>We propose the use of SignWiring, a universal sign language transcription notation system, to serve as an intermediary link between the visual-gestural modality of signed languages and text-based linguistic representations.
  arXiv  Detail & Related papers  (2024-12-02T21:51:41Z)
• Signs as Tokens: A Retrieval-Enhanced Multilingual Sign Language Generator [55.94334001112357]
  We introduce a multilingual sign language model, Signs as Tokens (SOKE), which can generate 3D sign avatars autoregressively from text inputs.<n>We propose a retrieval-enhanced SLG approach, which incorporates external sign dictionaries to provide accurate word-level signs.
  arXiv  Detail & Related papers  (2024-11-26T18:28:09Z)
• Leveraging the Power of MLLMs for Gloss-Free Sign Language Translation [14.817951264354022]
  Sign language translation (SLT) is a challenging task that involves translating sign language images into spoken language.<n>We propose a novel gloss-free framework called Multimodal Sign Language Translation (MMSLT)<n>Our approach achieves state-of-the-art performance on benchmark datasets PHOENIX14T and CSL-Daily.
  arXiv  Detail & Related papers  (2024-11-25T09:01:41Z)
• SCOPE: Sign Language Contextual Processing with Embedding from LLMs [49.5629738637893]
  Sign languages, used by around 70 million Deaf individuals globally, are visual languages that convey visual and contextual information. Current methods in vision-based sign language recognition ( SLR) and translation (SLT) struggle with dialogue scenes due to limited dataset diversity and the neglect of contextually relevant information. We introduce SCOPE, a novel context-aware vision-based SLR and SLT framework.
  arXiv  Detail & Related papers  (2024-09-02T08:56:12Z)
• When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models [130.40123493752816]
  This survey provides a comprehensive overview of the methodologies enabling large language models to process, understand, and generate 3D data.<n>Our investigation spans various 3D data representations, from point clouds to Neural Radiance Fields (NeRFs)<n>It examines their integration with LLMs for tasks such as 3D scene understanding, captioning, question-answering, and dialogue.
  arXiv  Detail & Related papers  (2024-05-16T16:59:58Z)
• SignAvatars: A Large-scale 3D Sign Language Holistic Motion Dataset and Benchmark [20.11364909443987]
  SignAvatars is the first large-scale, multi-prompt 3D sign language (SL) motion dataset designed to bridge the communication gap for Deaf and hard-of-hearing individuals. The dataset comprises 70,000 videos from 153 signers, totaling 8.34 million frames, covering both isolated signs and continuous, co-articulated signs.
  arXiv  Detail & Related papers  (2023-10-31T13:15:49Z)
• Soft Language Clustering for Multilingual Model Pre-training [57.18058739931463]
  We propose XLM-P, which contextually retrieves prompts as flexible guidance for encoding instances conditionally. Our XLM-P enables (1) lightweight modeling of language-invariant and language-specific knowledge across languages, and (2) easy integration with other multilingual pre-training methods.
  arXiv  Detail & Related papers  (2023-06-13T08:08:08Z)
• Towards Language-guided Interactive 3D Generation: LLMs as Layout Interpreter with Generative Feedback [20.151147653552155]
  Large Language Models (LLMs) have demonstrated impressive reasoning, conversational, and zero-shot generation abilities. We propose a novel language-guided interactive 3D generation system, dubbed LI3D, that integrates LLMs as a 3D layout interpreter. Our system also incorporates LLaVA, a large language and vision assistant, to provide generative feedback from the visual aspect for improving the visual quality of generated content.
  arXiv  Detail & Related papers  (2023-05-25T07:43:39Z)
• LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation [94.33019040320507]
  Multimodal Machine Translation (MMT) focuses on enhancing text-only translation with visual features. Recent advances still struggle to train a separate model for each language pair, which is costly and unaffordable when the number of languages increases. We propose the Multilingual MMT task by establishing two new Multilingual MMT benchmark datasets covering seven languages.
  arXiv  Detail & Related papers  (2022-10-19T12:21:39Z)
• Generalizing Multimodal Pre-training into Multilingual via Language Acquisition [54.69707237195554]
  English-based Vision-Language Pre-training has achieved great success in various downstream tasks. Some efforts have been taken to generalize this success to non-English languages through Multilingual Vision-Language Pre-training. We propose a textbfMultitextbfLingual textbfAcquisition (MLA) framework that can easily generalize a monolingual Vision-Language Pre-training model into multilingual.
  arXiv  Detail & Related papers  (2022-05-29T08:53:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.