Gloss-free Sign Language Production (SLP) offers a direct translation of spoken language sentences into sign language, bypassing the need for gloss intermediaries. This paper presents the Sign language Vector Quantization Network, a novel approach to SLP that leverages Vector Quantization to derive discrete representations from sign pose sequences. Our method, rooted in both manual and non-manual elements of signing, supports advanced decoding methods and integrates latent-level alignment for enhanced linguistic coherence. Through comprehensive evaluations, we demonstrate superior performance of our method over prior SLP methods and highlight the reliability of Back-Translation and Fr\'echet Gesture Distance as evaluation metrics.
@article{arxiv.2309.12179,
title = {Autoregressive Sign Language Production: A Gloss-Free Approach with Discrete Representations},
author = {Eui Jun Hwang and Huije Lee and Jong C. Park},
journal= {arXiv preprint arXiv:2309.12179},
year = {2024}
}