# Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition

arXiv: https://arxiv.org/abs/2203.07996 · HTML: https://mlsanity.com/paper/2203.07996/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 24 Feb 2022.

## Builds on (most cited first, 26 of 26)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [Deep Audio-Visual Speech Recognition](https://mlsanity.com/paper/1809.02108/) (2018)
- [LRS3-TED: a large-scale dataset for visual speech recognition](https://mlsanity.com/paper/1809.00496/) (2018)
- [Lip Reading Sentences in the Wild](https://mlsanity.com/paper/1611.05358/) (2016)
- [End-to-end Audio-visual Speech Recognition with Conformers](https://mlsanity.com/paper/2102.06657/) (2021)
- [Lipreading using Temporal Convolutional Networks](https://mlsanity.com/paper/2001.08702/) (2020)
- [ASR is all you need: cross-modal distillation for lip reading](https://mlsanity.com/paper/1911.12747/) (2019)
- [Combining Residual Networks with LSTMs for Lipreading](https://mlsanity.com/paper/1703.04105/) (2017)
- [Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture](https://mlsanity.com/paper/1810.00108/) (2018)
- [Hearing Lips: Improving Lip Reading by Distilling Speech Recognizers](https://mlsanity.com/paper/1911.11502/) (2019)
- [Audio-visual Recognition of Overlapped speech for the LRS2 dataset](https://mlsanity.com/paper/2001.01656/) (2020)
- [Visually Guided Self Supervised Learning of Speech Representations](https://mlsanity.com/paper/2001.04316/) (2020)

## Built on by (most cited first, 12 of 12)

- [VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning](https://mlsanity.com/paper/2211.11275/) (2022)
- [Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs](https://mlsanity.com/paper/2411.02256/) (2024)
- [A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2403.04245/) (2024)
- [Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2305.09212/) (2023)
- [Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition](https://mlsanity.com/paper/2306.10563/) (2023)
- [Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation](https://mlsanity.com/paper/2504.18539/) (2025)
- [MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2306.10567/) (2023)
- [MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition](https://mlsanity.com/paper/2502.10447/) (2025)
- [UniBriVL: Robust Universal Representation and Generation of Audio Driven Diffusion Models](https://mlsanity.com/paper/2307.15898/) (2023)
- [LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition](https://mlsanity.com/paper/2406.04432/) (2024)
- [CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization](https://mlsanity.com/paper/2505.03186/) (2025)
- [OCR-Enhanced Multimodal ASR Can Read While Listening](https://mlsanity.com/paper/2601.18393/) (2026)

## Abstract (arXiv)

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, although the effectiveness of large-scale self-supervised learning is well established in both audio and visual modalities, how to integrate those pre-trained models into a multimodal scenario remains underexplored. In this work, we successfully leverage unimodal self-supervised learning to promote the multimodal AVSR. In particular, audio and visual front-ends are trained on large-scale unimodal datasets, then we integrate components of both front-ends into a larger multimodal framework which learns to recognize parallel audio-visual data into characters through a combination of CTC and seq2seq decoding. We show that both components inherited from unimodal self-supervised learning cooperate well, resulting in that the multimodal framework yields competitive results through fine-tuning. Our model is experimentally validated on both word-level and sentence-level tasks. Especially, even without an external language model, our proposed model raises the state-of-the-art performances on the widely accepted Lip Reading Sentences 2 (LRS2) dataset by a large margin, with a relative improvement of 30%.