PulseAugur
EN
LIVE 13:23:08

LLMs boost sign language translation with synthetic video data

Researchers have developed a novel method to augment sign language translation (SLT) datasets using large language models (LLMs). This approach generates synthetic video-text pairs by extracting clips from existing gloss-annotated corpora and using an LLM to create new sentence glosses. The synthetic data significantly improves SLT performance, achieving a 2.92 BLEU-4 gain over a baseline, without requiring additional human annotation or generative video models. The study also found that optimizing for visual smoothness in clip transitions can be counterproductive, suggesting abrupt boundaries may offer implicit regularization. AI

IMPACT Enhances sign language translation capabilities by creating larger, more diverse training datasets, potentially improving accessibility for the deaf and hard-of-hearing community.

RANK_REASON Academic paper detailing a new methodology for corpus augmentation in sign language translation.

Read on arXiv cs.LG →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

COVERAGE [2]

  1. arXiv cs.LG TIER_1 English(EN) · Zsolt Robotka, \'Ad\'am R\'ak, Jalal Al-Afandi, Andr\'as Horv\'ath, Gy\"orgy Cserey ·

    Corpus Augmentation for Sign Language Translation via LLM-Guided Video Stitching

    arXiv:2606.11925v1 Announce Type: cross Abstract: Sign language translation (SLT) converts sign language video into spoken language text and holds significant promise for improving accessibility and enabling communication between signing and non-signing communities. While large w…

  2. arXiv cs.LG TIER_1 English(EN) · György Cserey ·

    Corpus Augmentation for Sign Language Translation via LLM-Guided Video Stitching

    Sign language translation (SLT) converts sign language video into spoken language text and holds significant promise for improving accessibility and enabling communication between signing and non-signing communities. While large weakly-aligned datasets have enabled pre-training a…