Cover Image

Mitigating Attention Sinks and Massive Activations in Audio-Visual Speech Recognition with LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Anand, Cappellazzo, Umberto, Petridis, Stavros, Pantic, Maja
Format:	Preprint
Published:	2025
Subjects:	Audio and Speech Processing Computer Vision and Pattern Recognition Sound
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition
by: Cappellazzo, Umberto, et al.
Published: (2026)

Adaptive Audio-Visual Speech Recognition via Matryoshka-Based Multimodal LLMs
by: Cappellazzo, Umberto, et al.
Published: (2025)

MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition
by: Cappellazzo, Umberto, et al.
Published: (2025)

Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models
by: Cappellazzo, Umberto, et al.
Published: (2025)

Large Language Models are Strong Audio-Visual Speech Recognition Learners
by: Cappellazzo, Umberto, et al.
Published: (2024)

RT-LA-VocE: Real-Time Low-SNR Audio-Visual Speech Enhancement
by: Chen, Honglie, et al.
Published: (2024)

Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach
by: Cappellazzo, Umberto, et al.
Published: (2025)

Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations
by: Yeo, Jeong Hun, et al.
Published: (2025)

Full-Rank No More: Low-Rank Weight Training for Modern Speech Recognition Models
by: Fernandez-Lopez, Adriana, et al.
Published: (2024)

Audio-visual video-to-speech synthesis with synthesized input audio
by: Kefalas, Triantafyllos, et al.
Published: (2023)

Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation
by: Rouditchenko, Andrew, et al.
Published: (2024)

mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition
by: Rouditchenko, Andrew, et al.
Published: (2025)

AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition
by: Liu, Zehua, et al.
Published: (2024)

IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation
by: Li, Kai, et al.
Published: (2023)

Enhancing CTC-Based Visual Speech Recognition
by: Laux, Hendrik, et al.
Published: (2024)

Seeing Speech and Sound: Distinguishing and Locating Audios in Visual Scenes
by: Ryu, Hyeonggon, et al.
Published: (2025)

Large-scale unsupervised audio pre-training for video-to-speech synthesis
by: Kefalas, Triantafyllos, et al.
Published: (2023)

Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation
by: Kim, Minsu, et al.
Published: (2024)

AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition
by: Xue, Junxiao, et al.
Published: (2025)

SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition
by: Wang, Hao, et al.
Published: (2024)

MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens
by: Yeo, Jeong Hun, et al.
Published: (2025)

Cross Attentional Audio-Visual Fusion for Dimensional Emotion Recognition
by: Praveen, R. Gnana, et al.
Published: (2021)

Audio-Visual Person Verification based on Recursive Fusion of Joint Cross-Attention
by: Praveen, R. Gnana, et al.
Published: (2024)

Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction
by: Kim, Minsu, et al.
Published: (2025)

RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation
by: Pegg, Samuel, et al.
Published: (2023)

CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge
by: Liu, Zehua, et al.
Published: (2025)

Mitigating Audiovisual Mismatch in Visual-Guide Audio Captioning
by: Xu, Le, et al.
Published: (2025)

Bootstrapping Audio-Visual Segmentation by Strengthening Audio Cues
by: Chen, Tianxiang, et al.
Published: (2024)

Dynamic Data Pruning for Automatic Speech Recognition
by: Xiao, Qiao, et al.
Published: (2024)

AISHELL6-whisper: A Chinese Mandarin Audio-visual Whisper Speech Dataset with Speech Recognition Baselines
by: Li, Cancan, et al.
Published: (2025)

CCStereo: Audio-Visual Contextual and Contrastive Learning for Binaural Audio Generation
by: Chen, Yuanhong, et al.
Published: (2025)

Dynamic Derivation and Elimination: Audio Visual Segmentation with Enhanced Audio Semantics
by: Liu, Chen, et al.
Published: (2025)

Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing
by: Liu, Zehua, et al.
Published: (2025)

DDAVS: Disentangled Audio Semantics and Delayed Bidirectional Alignment for Audio-Visual Segmentation
by: Tian, Jingqi, et al.
Published: (2025)

Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling
by: Du, Jiarong, et al.
Published: (2025)

United we stand, Divided we fall: Handling Weak Complementary Relationships for Audio-Visual Emotion Recognition in Valence-Arousal Space
by: Praveen, R. Gnana, et al.
Published: (2025)

Discrepancy-Aware Attention Network for Enhanced Audio-Visual Zero-Shot Learning
by: Yu, RunLin, et al.
Published: (2024)

DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation
by: Zhang, Haomin, et al.
Published: (2025)

A Joint Cross-Attention Model for Audio-Visual Fusion in Dimensional Emotion Recognition
by: Praveen, R. Gnana, et al.
Published: (2022)

Oceanship: A Large-Scale Dataset for Underwater Audio Target Recognition
by: Li, Zeyu, et al.
Published: (2024)