# AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR

arXiv: https://arxiv.org/abs/2303.16501 · HTML: https://mlsanity.com/paper/2303.16501/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 45 references that are in the map.
- First posted on arXiv 29 Mar 2023.

## Builds on (most cited first, 30 of 36)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Ego4D: Around the World in 3,000 Hours of Egocentric Video](https://mlsanity.com/paper/2110.07058/) (2021)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips](https://mlsanity.com/paper/1906.03327/) (2019)
- [ClipCap: CLIP Prefix for Image Captioning](https://mlsanity.com/paper/2111.09734/) (2021)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [Libri-Light: A Benchmark for ASR with Limited or No Supervision](https://mlsanity.com/paper/1912.07875/) (2019)
- [W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Training](https://mlsanity.com/paper/2108.06209/) (2021)
- [Deep Audio-Visual Speech Recognition](https://mlsanity.com/paper/1809.02108/) (2018)
- [VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks](https://mlsanity.com/paper/2112.06825/) (2021)
- [Zero-Shot Video Question Answering via Frozen Bidirectional Language Models](https://mlsanity.com/paper/2206.08155/) (2022)
- [Lip Reading Sentences in the Wild](https://mlsanity.com/paper/1611.05358/) (2016)
- [Pushing the Limits of Semi-Supervised Learning for Automatic Speech Recognition](https://mlsanity.com/paper/2010.10504/) (2020)
- [Self-supervised Learning with Random-projection Quantizer for Speech Recognition](https://mlsanity.com/paper/2202.01855/) (2022)
- [End-to-end Audio-visual Speech Recognition with Conformers](https://mlsanity.com/paper/2102.06657/) (2021)
- [How2: A Large-scale Dataset for Multimodal Language Understanding](https://mlsanity.com/paper/1811.00347/) (2018)
- [End-to-end ASR: from Supervised to Semi-Supervised Learning with Modern Architectures](https://mlsanity.com/paper/1911.08460/) (2019)
- [Self-training and Pre-training are Complementary for Speech Recognition](https://mlsanity.com/paper/2010.11430/) (2020)
- [MAGMA -- Multimodal Augmentation of Generative Models through Adapter-based Finetuning](https://mlsanity.com/paper/2112.05253/) (2021)
- [Recurrent Neural Network Transducer for Audio-Visual Speech Recognition](https://mlsanity.com/paper/1911.04890/) (2019)
- [End-to-end Audiovisual Speech Recognition](https://mlsanity.com/paper/1802.06424/) (2018)
- [AVATAR: Unconstrained Audiovisual Speech Recognition](https://mlsanity.com/paper/2206.07684/) (2022)

## Built on by (most cited first, 16 of 16)

- [OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models](https://mlsanity.com/paper/2602.04804/) (2026)
- [MeLFusion: Synthesizing Music from Image and Language Cues using Diffusion Models](https://mlsanity.com/paper/2406.04673/) (2024)
- [XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception](https://mlsanity.com/paper/2403.14402/) (2024)
- [SpeechQE: Estimating the Quality of Direct Speech Translation](https://mlsanity.com/paper/2410.21485/) (2024)
- [Robust Audiovisual Speech Recognition Models with Mixture-of-Experts](https://mlsanity.com/paper/2409.12370/) (2024)
- [Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation](https://mlsanity.com/paper/2504.18539/) (2025)
- [MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition](https://mlsanity.com/paper/2502.10447/) (2025)
- [Survey of End-to-End Multi-Speaker Automatic Speech Recognition for Monaural Audio](https://mlsanity.com/paper/2505.10975/) (2025)
- [SynesLM: A Unified Approach for Audio-visual Speech Recognition and Translation via Language Model and Synthetic Data](https://mlsanity.com/paper/2408.00624/) (2024)
- [Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models](https://mlsanity.com/paper/2502.01709/) (2025)
- [Exploring the Potential of Multimodal LLM with Knowledge-Intensive Multimodal ASR](https://mlsanity.com/paper/2406.10880/) (2024)
- [Visual-Aware Speech Recognition for Noisy Scenarios](https://mlsanity.com/paper/2504.07229/) (2025)
- [MLLM-based Speech Recognition: When and How is Multimodality Beneficial?](https://mlsanity.com/paper/2507.19037/) (2025)
- [Speech Recognition on TV Series with Video-guided Post-ASR Correction](https://mlsanity.com/paper/2506.07323/) (2025)
- [AVSRBench: A Multi-Condition AVSR Benchmark](https://mlsanity.com/paper/2609.10366/) (2026)
- [Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2609.10394/) (2026)

## Abstract (arXiv)

Audiovisual automatic speech recognition (AV-ASR) aims to improve the robustness of a speech recognition system by incorporating visual information. Training fully supervised multimodal models for this task from scratch, however is limited by the need for large labelled audiovisual datasets (in each downstream domain of interest). We present AVFormer, a simple method for augmenting audio-only models with visual information, at the same time performing lightweight domain adaptation. We do this by (i) injecting visual embeddings into a frozen ASR model using lightweight trainable adaptors. We show that these can be trained on a small amount of weakly labelled video data with minimum additional training time and parameters. (ii) We also introduce a simple curriculum scheme during training which we show is crucial to enable the model to jointly process audio and visual information effectively; and finally (iii) we show that our model achieves state of the art zero-shot results on three different AV-ASR benchmarks (How2, VisSpeech and Ego4D), while also crucially preserving decent performance on traditional audio-only speech recognition benchmarks (LibriSpeech). Qualitative results show that our model effectively leverages visual information for robust speech recognition.