# Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization

arXiv: https://arxiv.org/abs/2504.06610 · HTML: https://mlsanity.com/paper/2504.06610/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 9 Apr 2025.

## Builds on (most cited first, 20 of 20)

- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Generating Sentences from a Continuous Space](https://mlsanity.com/paper/1511.06349/) (2015)
- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [Ladder Variational Autoencoders](https://mlsanity.com/paper/1602.02282/) (2016)
- [Semi-supervised Sequence Learning](https://mlsanity.com/paper/1511.01432/) (2015)
- [Cyclical Annealing Schedule: A Simple Approach to Mitigating KL Vanishing](https://mlsanity.com/paper/1903.10145/) (2019)
- [Improving Sign Language Translation with Monolingual Data by Sign Back-Translation](https://mlsanity.com/paper/2105.12397/) (2021)
- [Progressive Transformers for End-to-End Sign Language Production](https://mlsanity.com/paper/2004.14874/) (2020)
- [Adversarial Training for Multi-Channel Sign Language Production](https://mlsanity.com/paper/2008.12405/) (2020)
- [Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks](https://mlsanity.com/paper/2103.06982/) (2021)
- [Neural Sign Actors: A diffusion model for 3D sign language production from text](https://mlsanity.com/paper/2312.02702/) (2023)
- [G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model](https://mlsanity.com/paper/2208.09141/) (2022)
- [T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text](https://mlsanity.com/paper/2406.07119/) (2024)
- [Machine Translation between Spoken Languages and Signed Languages Represented in SignWriting](https://mlsanity.com/paper/2210.05404/) (2022)
- [A Data-Driven Representation for Sign Language Production](https://mlsanity.com/paper/2404.11499/) (2024)
- [Improving 3D Pose Estimation for Sign Language](https://mlsanity.com/paper/2308.09525/) (2023)
- [Changing the Representation: Examining Language Representation for Neural Sign Language Production](https://mlsanity.com/paper/2210.06312/) (2022)
- [Autoregressive Sign Language Production: A Gloss-Free Approach with Discrete Representations](https://mlsanity.com/paper/2309.12179/) (2023)
- [Sign Stitching: A Novel Approach to Sign Language Production](https://mlsanity.com/paper/2405.07663/) (2024)
- [Non-Autoregressive Sign Language Production via Knowledge Distillation](https://mlsanity.com/paper/2208.06183/) (2022)

## Built on by (most cited first, 5 of 5)

- [SLRTP2025 Sign Language Production Challenge: Methodology, Results, and Future Work](https://mlsanity.com/paper/2508.06951/) (2025)
- [Phonological Representation Learning for Isolated Signs Improves Out-of-Vocabulary Generalization](https://mlsanity.com/paper/2509.04745/) (2025)
- [Towards Skeletal and Signer Noise Reduction in Sign Language Production via Quaternion-Based Pose Encoding and Contrastive Learning](https://mlsanity.com/paper/2508.14574/) (2025)
- [A2V-SLP: Alignment-Aware Variational Modeling for Disentangled Sign Language Production](https://mlsanity.com/paper/2602.11861/) (2026)
- [The Impact of VAE Design on Latent Pose Representations for Diffusion-based Sign Language Production](https://mlsanity.com/paper/2606.22959/) (2026)

## Abstract (arXiv)

In this work, we propose DARSLP, a simple gloss-free, transformer-based sign language production (SLP) framework that directly maps spoken-language text to sign pose sequences. We first train a pose autoencoder that encodes sign poses into a compact latent space using an articulator-based disentanglement strategy, where features corresponding to the face, right hand, left hand, and body are modeled separately to promote structured and interpretable representation learning. Next, a non-autoregressive transformer decoder is trained to predict these latent representations from word-level text embeddings of the input sentence. To guide this process, we apply channel-aware regularization by aligning predicted latent distributions with priors extracted from the ground-truth encodings using a KL divergence loss. The contribution of each channel to the loss is weighted according to its associated articulator region, enabling the model to account for the relative importance of different articulators during training. Our approach does not rely on gloss supervision or pretrained models, and achieves state-of-the-art results on the PHOENIX14T and CSL-Daily datasets.