# JEP-KD: Joint-Embedding Predictive Architecture Based Knowledge Distillation for Visual Speech Recognition

arXiv: https://arxiv.org/abs/2403.18843 · HTML: https://mlsanity.com/paper/2403.18843/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Speech and audio distillation, one of 12 directions in Knowledge distillation.
- Builds on 17 of its 30 references that are in the map.
- First posted on arXiv 4 Mar 2024.

## Placed in

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

## Builds on (most cited first, 17 of 17)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture](https://mlsanity.com/paper/2301.08243/) (2023)
- [Least Squares Generative Adversarial Networks](https://mlsanity.com/paper/1611.04076/) (2016)
- [MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis](https://mlsanity.com/paper/1910.06711/) (2019)
- [Kornia: an Open Source Differentiable Computer Vision Library for PyTorch](https://mlsanity.com/paper/1910.02190/) (2019)
- [WenetSpeech: A 10000+ Hours Multi-domain Mandarin Corpus for Speech Recognition](https://mlsanity.com/paper/2110.03370/) (2021)
- [WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2102.01547/) (2021)
- [Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels](https://mlsanity.com/paper/2303.14307/) (2023)
- [Visual Speech Recognition for Multiple Languages in the Wild](https://mlsanity.com/paper/2202.13084/) (2022)
- [WeNet 2.0: More Productive End-to-End Speech Recognition Toolkit](https://mlsanity.com/paper/2203.15455/) (2022)
- [Towards Practical Lipreading with Distilled and Efficient Models](https://mlsanity.com/paper/2007.06504/) (2020)
- [LiRA: Learning Visual Speech Representations from Audio through Self-supervision](https://mlsanity.com/paper/2106.09171/) (2021)
- [Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers](https://mlsanity.com/paper/1911.11502/) (2019)
- [Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading](https://mlsanity.com/paper/2204.01725/) (2022)
- [A Cascade Sequence-to-Sequence Model for Chinese Mandarin Lip Reading](https://mlsanity.com/paper/1908.04917/) (2019)
- [Advances and Challenges in Deep Lip Reading](https://mlsanity.com/paper/2110.07879/) (2021)

## Abstract (arXiv)

Visual Speech Recognition (VSR) tasks are generally recognized to have a lower theoretical performance ceiling than Automatic Speech Recognition (ASR), owing to the inherent limitations of conveying semantic information visually. To mitigate this challenge, this paper introduces an advanced knowledge distillation approach using a Joint-Embedding Predictive Architecture (JEPA), named JEP-KD, designed to more effectively utilize audio features during model training. Central to JEP-KD is the inclusion of a generative network within the embedding layer, which enhances the video encoder's capacity for semantic feature extraction and brings it into closer alignment with the audio features from a pre-trained ASR model's encoder. This approach aims to progressively reduce the performance gap between VSR and ASR. Moreover, a comprehensive multimodal, multistage training regimen for the JEP-KD framework is established, bolstering the robustness and efficacy of the training process. Experiment results demonstrate that JEP-KD significantly improves the performance of VSR models and demonstrates versatility across different VSR platforms, indicating its potential for broader application within other multimodal tasks.