# AVSRBench: A Multi-Condition AVSR Benchmark

arXiv: https://arxiv.org/abs/2609.10366 · HTML: https://mlsanity.com/paper/2609.10366/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 35 of its 53 references that are in the map.
- First posted on arXiv 9 Sep 2026.

## Builds on (most cited first, 30 of 35)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [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)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [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)
- [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://mlsanity.com/paper/1804.03619/) (2018)
- [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)
- [Robust Self-Supervised Audio-Visual Speech Recognition](https://mlsanity.com/paper/2201.01763/) (2022)
- [Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring](https://mlsanity.com/paper/2303.08536/) (2023)
- [Large Language Models are Strong Audio-Visual Speech Recognition Learners](https://mlsanity.com/paper/2409.12319/) (2024)
- [Deep Learning for Visual Speech Analysis: A Survey](https://mlsanity.com/paper/2205.10839/) (2022)
- [SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision](https://mlsanity.com/paper/2303.17200/) (2023)
- [MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens](https://mlsanity.com/paper/2503.11315/) (2025)
- [AVFormer: Injecting Vision into Frozen Speech Models for Zero-Shot AV-ASR](https://mlsanity.com/paper/2303.16501/) (2023)
- [SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization](https://mlsanity.com/paper/2406.12233/) (2024)
- [Do VSR Models Generalize Beyond LRS3?](https://mlsanity.com/paper/2311.14063/) (2023)
- [Cocktail-Party Audio-Visual Speech Recognition](https://mlsanity.com/paper/2506.02178/) (2025)
- [Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction](https://mlsanity.com/paper/2507.18863/) (2025)
- [Investigating the Lombard Effect Influence on End-to-End Audio-Visual Speech Recognition](https://mlsanity.com/paper/1906.02112/) (2019)
- [Uncovering the Visual Contribution in Audio-Visual Speech Recognition](https://mlsanity.com/paper/2412.17129/) (2024)
- [From Hype to Insight: Rethinking Large Language Model Integration in Visual Speech Recognition](https://mlsanity.com/paper/2509.14880/) (2025)
- [A Cocktail-Party Benchmark: Multi-Modal dataset and Comparative Evaluation Results](https://mlsanity.com/paper/2510.23276/) (2025)
- [The Lipreading Gap: Do VSR Models Perceive Visual Speech Like Human Lipreaders?](https://mlsanity.com/paper/2606.07435/) (2026)
- [Seeing the Context: Rich Visual Context-Aware Speech Recognition via Multimodal Reasoning](https://mlsanity.com/paper/2603.07263/) (2026)
- [When AVSR Meets Video Conferencing: Dataset, Degradation, and the Hidden Mechanism Behind Performance Collapse](https://mlsanity.com/paper/2603.22915/) (2026)

## Abstract (arXiv)

While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true generalization or just domain adaptation. To investigate this gap, we evaluate three AVSR architectures across six conditions: controlled broadcast speech, fixed-grammar utterances, hyper-articulated Lombard speech, read speech from professional lipspeakers and non-professional speakers, and spontaneous multi-party video conversations. We find that visual-only performance deteriorates rapidly beyond broadcast domains, and audio-video fusion mainly benefits Lombard speech environments. Visual understanding degrades sharply at 90deg profile views, with multimodal systems relying largely on acoustic fallback. Additionally, speaker articulation proves more critical than minor camera shifts, and LLM-based architectures suffer from poor out-of-domain generalization. Our work highlights a significant generalization gap in current AVSR research. To address this, we also introduce RoomReader-AV as a new benchmark for AVSR and release a unified data preprocessing pipeline to make comprehensive multi-condition evaluation accessible.