# Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder

arXiv: https://arxiv.org/abs/2601.18396 · HTML: https://mlsanity.com/paper/2601.18396/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 26 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 20 of 20)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Flamingo: a Visual Language Model for Few-Shot Learning](https://mlsanity.com/paper/2204.14198/) (2022)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [MUSAN: A Music, Speech, and Noise Corpus](https://mlsanity.com/paper/1510.08484/) (2015)
- [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)
- [Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels](https://mlsanity.com/paper/2303.14307/) (2023)
- [Robust Self-Supervised Audio-Visual Speech Recognition](https://mlsanity.com/paper/2201.01763/) (2022)
- [Large Language Models are Strong Audio-Visual Speech Recognition Learners](https://mlsanity.com/paper/2409.12319/) (2024)
- [MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation](https://mlsanity.com/paper/2303.00628/) (2023)
- [Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation](https://mlsanity.com/paper/2406.10082/) (2024)
- [Audio-Visual Efficient Conformer for Robust Speech Recognition](https://mlsanity.com/paper/2301.01456/) (2023)
- [MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens](https://mlsanity.com/paper/2503.11315/) (2025)
- [MLCA-AVSR: Multi-Layer Cross Attention Fusion based Audio-Visual Speech Recognition](https://mlsanity.com/paper/2401.03424/) (2024)
- [Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition](https://mlsanity.com/paper/2407.03563/) (2024)
- [Multi-Encoder Learning and Stream Fusion for Transformer-Based End-to-End Automatic Speech Recognition](https://mlsanity.com/paper/2104.00120/) (2021)
- [Self-Supervised Adaptive AV Fusion Module for Pre-Trained ASR Models](https://mlsanity.com/paper/2312.13873/) (2023)
- [mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition](https://mlsanity.com/paper/2502.01547/) (2025)
- [Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models](https://mlsanity.com/paper/2502.01709/) (2025)

## Built on by (most cited first, 2 of 2)

- [VIB-AVSR: Variational Information Bottleneck for Noise-Robust LLM-Based Audio-Visual Speech Recognition](https://mlsanity.com/paper/2606.29632/) (2026)
- [From Speech to Interaction: Analyzing Multimodal Systems in Cocktail-Party Scenarios](https://mlsanity.com/paper/2608.08510/) (2026)

## Abstract (arXiv)

In audiovisual automatic speech recognition (AV-ASR) systems, information fusion of visual features in a pre-trained ASR has been proven as a promising method to improve noise robustness. In this work, based on the prominent Whisper ASR, first, we propose a simple and effective visual fusion method -- use of visual features both in encoder and decoder (dual-use) -- to learn the audiovisual interactions in the encoder and to weigh modalities in the decoder. Second, we compare visual fusion methods in Whisper models of various sizes. Our proposed dual-use method shows consistent noise robustness improvement, e.g., a 35% relative improvement (WER: 4.41% vs. 6.83%) based on Whisper small, and a 57% relative improvement (WER: 4.07% vs. 9.53%) based on Whisper medium, compared to typical reference middle fusion in babble noise with a signal-to-noise ratio (SNR) of 0dB. Third, we conduct ablation studies examining the impact of various module designs and fusion options. Fine-tuned on 1929 hours of audiovisual data, our dual-use method using Whisper medium achieves 4.08% (MUSAN babble noise) and 4.43% (NoiseX babble noise) average WER across various SNRs, thereby establishing a new state-of-the-art in noisy conditions on the LRS3 AV-ASR benchmark. Our code is at https://github.com/ifnspaml/Dual-Use-AVASR