# Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations

arXiv: https://arxiv.org/abs/2503.06273 · HTML: https://mlsanity.com/paper/2503.06273/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 56 of its 72 references that are in the map.
- First posted on arXiv 8 Mar 2025.

## Builds on (most cited first, 30 of 56)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Mistral 7B](https://mlsanity.com/paper/2310.06825/) (2023)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [SALMONN: Towards Generic Hearing Abilities for Large Language Models](https://mlsanity.com/paper/2310.13289/) (2023)
- [Deep Speech 2: End-to-End Speech Recognition in English and Mandarin](https://mlsanity.com/paper/1512.02595/) (2015)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Generative Spoken Language Modeling from Raw Audio](https://mlsanity.com/paper/2102.01192/) (2021)
- [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)
- [Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction](https://mlsanity.com/paper/2201.02184/) (2022)
- [Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learning](https://mlsanity.com/paper/1609.06773/) (2016)
- [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://mlsanity.com/paper/1804.03619/) (2018)
- [End-to-end Audio-visual Speech Recognition with Conformers](https://mlsanity.com/paper/2102.06657/) (2021)
- [Unsupervised Speech Recognition](https://mlsanity.com/paper/2105.11084/) (2021)
- [End-to-End Speech Recognition: A Survey](https://mlsanity.com/paper/2303.03329/) (2023)
- [Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels](https://mlsanity.com/paper/2303.14307/) (2023)
- [The Multilingual TEDx Corpus for Speech Recognition and Translation](https://mlsanity.com/paper/2102.01757/) (2021)
- [Visual Speech Recognition for Multiple Languages in the Wild](https://mlsanity.com/paper/2202.13084/) (2022)
- [Universal Phone Recognition with a Multilingual Allophone System](https://mlsanity.com/paper/2002.11800/) (2020)
- [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)

## Built on by (most cited first, 9 of 9)

- [Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs](https://mlsanity.com/paper/2510.22603/) (2025)
- [MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2510.04136/) (2025)
- [Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models](https://mlsanity.com/paper/2511.07253/) (2025)
- [The Lipreading Gap: Do VSR Models Perceive Visual Speech Like Human Lipreaders?](https://mlsanity.com/paper/2606.07435/) (2026)
- [When AVSR Meets Video Conferencing: Dataset, Degradation, and the Hidden Mechanism Behind Performance Collapse](https://mlsanity.com/paper/2603.22915/) (2026)
- [MLLM-based Speech Recognition: When and How is Multimodality Beneficial?](https://mlsanity.com/paper/2507.19037/) (2025)
- [TD3Net: A temporal densely connected multi-dilated convolutional network for lipreading](https://mlsanity.com/paper/2506.16073/) (2025)
- [Seeing is Believing: Emotion-Aware Audio-Visual Language Modeling for Expressive Speech Generation](https://mlsanity.com/paper/2508.16188/) (2025)
- [Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2609.10394/) (2026)

## Abstract (arXiv)

We explore a novel zero-shot Audio-Visual Speech Recognition (AVSR) framework, dubbed Zero-AVSR, which enables speech recognition in target languages without requiring any audio-visual speech data in those languages. Specifically, we introduce the Audio-Visual Speech Romanizer (AV-Romanizer), which learns language-agnostic speech representations by predicting Roman text. Then, by leveraging the strong multilingual modeling capabilities of Large Language Models (LLMs), we propose converting the predicted Roman text into language-specific graphemes, forming the proposed Cascaded Zero-AVSR. Taking it a step further, we explore a unified Zero-AVSR approach by directly integrating the audio-visual speech representations encoded by the AV-Romanizer into the LLM. This is achieved through finetuning the adapter and the LLM using our proposed multi-task learning scheme. To capture the wide spectrum of phonetic and linguistic diversity, we also introduce a Multilingual Audio-Visual Romanized Corpus (MARC) consisting of 2,916 hours of audio-visual speech data across 82 languages, along with transcriptions in both language-specific graphemes and Roman text. Extensive analysis and experiments confirm that the proposed Zero-AVSR framework has the potential to expand language support beyond the languages seen during the training of the AV-Romanizer.