# Non-Autoregressive Sign Language Production via Knowledge Distillation

arXiv: https://arxiv.org/abs/2208.06183 · HTML: https://mlsanity.com/paper/2208.06183/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 18 of its 35 references that are in the map.
- First posted on arXiv 12 Aug 2022.

## Placed in

- Knowledge distillation / [Speech and audio distillation](https://mlsanity.com/distill/speech-and-audio-distillation/)

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1812.08008/) (2018)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [Sign Language Transformers: Joint End-to-end Sign Language Recognition and Translation](https://mlsanity.com/paper/2003.13830/) (2020)
- [Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity](https://mlsanity.com/paper/2009.02119/) (2020)
- [How2Sign: A Large-scale Multimodal Dataset for Continuous American Sign Language](https://mlsanity.com/paper/2008.08143/) (2020)
- [Progressive Transformers for End-to-End Sign Language Production](https://mlsanity.com/paper/2004.14874/) (2020)
- [Convolutional Sequence to Sequence Model for Human Dynamics](https://mlsanity.com/paper/1805.00655/) (2018)
- [Continuous 3D Multi-Channel Sign Language Production via Progressive Transformers and Mixture Density Networks](https://mlsanity.com/paper/2103.06982/) (2021)
- [Mixed SIGNals: Sign Language Production via a Mixture of Motion Primitives](https://mlsanity.com/paper/2107.11317/) (2021)
- [When Human Pose Estimation Meets Robustness: Adversarial Algorithms and Benchmarks](https://mlsanity.com/paper/2105.06152/) (2021)
- [Skeletor: Skeletal Transformers for Robust Body-Pose Estimation](https://mlsanity.com/paper/2104.11712/) (2021)
- [Multitask Non-Autoregressive Model for Human Motion Prediction](https://mlsanity.com/paper/2007.06426/) (2020)
- [Towards Developing a Multilingual and Code-Mixed Visual Question Answering System by Knowledge Distillation](https://mlsanity.com/paper/2109.04653/) (2021)

## Built on by (most cited first, 4 of 4)

- [T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text](https://mlsanity.com/paper/2406.07119/) (2024)
- [Disentangle and Regularize: Sign Language Production with Articulator-Based Disentanglement and Channel-Aware Regularization](https://mlsanity.com/paper/2504.06610/) (2025)
- [SIGNER: Temporally Grounded Sign Language Generation via Time-Resolved Conditioning](https://mlsanity.com/paper/2506.07460/) (2025)
- [A2V-SLP: Alignment-Aware Variational Modeling for Disentangled Sign Language Production](https://mlsanity.com/paper/2602.11861/) (2026)

## Abstract (arXiv)

Sign Language Production (SLP) aims to translate expressions in spoken language into corresponding ones in sign language, such as skeleton-based sign poses or videos. Existing SLP models are either AutoRegressive (AR) or Non-Autoregressive (NAR). However, AR-SLP models suffer from regression to the mean and error propagation during decoding. NSLP-G, a NAR-based model, resolves these issues to some extent but engenders other problems. For example, it does not consider target sign lengths and suffers from false decoding initiation. We propose a novel NAR-SLP model via Knowledge Distillation (KD) to address these problems. First, we devise a length regulator to predict the end of the generated sign pose sequence. We then adopt KD, which distills spatial-linguistic features from a pre-trained pose encoder to alleviate false decoding initiation. Extensive experiments show that the proposed approach significantly outperforms existing SLP models in both Frechet Gesture Distance and Back-Translation evaluation.