{"total":75,"rows":[{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"id":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114,"area":null},{"id":"2411.17558","title":"Natural Language Understanding and Inference with MLLM in Visual Question Answering: A Survey","created":"2024-11-26","cited_by_count":76,"area":"mllm"},{"id":"2311.15830","title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","created":"2023-11-27","cited_by_count":53,"area":null},{"id":"2207.11094","title":"Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videos","created":"2022-07-22","cited_by_count":50,"area":null},{"id":"2208.09579","title":"Learning in Audio-visual Context: A Review, Analysis, and New Perspective","created":"2022-08-20","cited_by_count":44,"area":null},{"id":"2409.12319","title":"Large Language Models are Strong Audio-Visual Speech Recognition Learners","created":"2024-09-18","cited_by_count":42,"area":"mllm"},{"id":"2207.07036","title":"u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality","created":"2022-07-14","cited_by_count":39,"area":null},{"id":"2303.00628","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation","created":"2023-03-01","cited_by_count":39,"area":null},{"id":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37,"area":null},{"id":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29,"area":null},{"id":"2305.19603","title":"Intelligible Lip-to-Speech Synthesis with Speech Units","created":"2023-05-31","cited_by_count":28,"area":null},{"id":"2302.06419","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","created":"2023-02-10","cited_by_count":27,"area":null},{"id":"2212.05301","title":"Leveraging Modality-specific Representations for Audio-visual Speech Recognition via Reinforcement Learning","created":"2022-12-10","cited_by_count":22,"area":null},{"id":"2402.05457","title":"It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition","created":"2024-02-08","cited_by_count":22,"area":null},{"id":"2305.17343","title":"Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser","created":"2023-05-27","cited_by_count":18,"area":null},{"id":"2405.04327","title":"Audio-Visual Speech Representation Expert for Enhanced Talking Face Video Generation and Evaluation","created":"2024-05-07","cited_by_count":17,"area":null},{"id":"2308.09311","title":"Lip Reading for Low-resource Languages by Learning and Combining General Speech Knowledge and Language-specific Knowledge","created":"2023-08-18","cited_by_count":16,"area":null},{"id":"2303.05309","title":"MixSpeech: Cross-Modality Self-Learning with Audio-Visual Stream Mixup for Visual Speech Translation and Recognition","created":"2023-03-09","cited_by_count":14,"area":null},{"id":"2312.02512","title":"AV2AV: Direct Audio-Visual Speech to Audio-Visual Speech Translation with Unified Audio-Visual Speech Representation","created":"2023-12-05","cited_by_count":14,"area":null},{"id":"2308.06112","title":"Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping","created":"2023-08-11","cited_by_count":12,"area":null},{"id":"2310.16754","title":"CAD -- Contextual Multi-modal Alignment for Dynamic AVQA","created":"2023-10-25","cited_by_count":10,"area":null},{"id":"2212.02782","title":"Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation","created":"2022-12-06","cited_by_count":9,"area":"distill"},{"id":"2305.09212","title":"Cross-Modal Global Interaction and Local Alignment for Audio-Visual Speech Recognition","created":"2023-05-16","cited_by_count":9,"area":null},{"id":"2311.14063","title":"Do VSR Models Generalize Beyond LRS3?","created":"2023-11-23","cited_by_count":9,"area":null},{"id":"2205.07180","title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT","created":"2022-05-15","cited_by_count":8,"area":null},{"id":"2306.10563","title":"Hearing Lips in Noise: Universal Viseme-Phoneme Mapping and Transfer for Robust Audio-Visual Speech Recognition","created":"2023-06-18","cited_by_count":7,"area":null},{"id":"2404.12725","title":"Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction","created":"2024-04-19","cited_by_count":7,"area":null},{"id":"2405.12983","title":"Multilingual Audio-Visual Speech Recognition with Hybrid CTC/RNN-T Fast Conformer","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2407.03563","title":"Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition","created":"2024-07-04","cited_by_count":7,"area":null},{"id":"2506.02178","title":"Cocktail-Party Audio-Visual Speech Recognition","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2309.08030","title":"AV2Wav: Diffusion-Based Re-synthesis from Continuous Self-supervised Features for Audio-Visual Speech Enhancement","created":"2023-09-14","cited_by_count":5,"area":"diffusion"},{"id":"2309.17395","title":"AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition","created":"2023-09-29","cited_by_count":5,"area":null},{"id":"2504.18539","title":"Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation","created":"2025-01-23","cited_by_count":5,"area":null},{"id":"2207.07935","title":"Visually-aware Acoustic Event Detection using Heterogeneous Graphs","created":"2022-07-16","cited_by_count":4,"area":null},{"id":"2306.10567","title":"MIR-GAN: Refining Frame-Level Modality-Invariant Representations with Adversarial Network for Audio-Visual Speech Recognition","created":"2023-06-18","cited_by_count":4,"area":null},{"id":"2307.02909","title":"Audio-visual End-to-end Multi-channel Speech Separation, Dereverberation and Recognition","created":"2023-07-06","cited_by_count":4,"area":null},{"id":"2411.09220","title":"Transferable Adversarial Attacks against ASR","created":"2024-11-14","cited_by_count":4,"area":null},{"id":"2502.01547","title":"mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2502.10447","title":"MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition","created":"2025-02-11","cited_by_count":4,"area":"moe"},{"id":"2507.21448","title":"Real-Time Audio-Visual Speech Enhancement Using Pre-trained Visual Representations","created":"2025-07-29","cited_by_count":4,"area":null},{"id":"2510.04136","title":"MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition","created":"2025-10-05","cited_by_count":4,"area":"moe"},{"id":"2511.07253","title":"Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2312.06613","title":"Neural Text to Articulate Talk: Deep Text to Audiovisual Speech Synthesis achieving both Auditory and Photo-realism","created":"2023-12-11","cited_by_count":3,"area":null},{"id":"2312.09369","title":"Audio-visual fine-tuning of audio-only ASR models","created":"2023-12-14","cited_by_count":3,"area":null},{"id":"2505.22088","title":"Visual Cues Support Robust Turn-taking Prediction in Noise","created":"2025-05-28","cited_by_count":3,"area":null},{"id":"2309.05843","title":"Optimizing Audio Augmentations for Contrastive Learning of Health-Related Acoustic Signals","created":"2023-09-11","cited_by_count":2,"area":null},{"id":"2310.05058","title":"Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2311.02733","title":"AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Deepfake Detection of Frontal Face Videos","created":"2023-11-05","cited_by_count":2,"area":null},{"id":"2409.09221","title":"Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2501.04038","title":"Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2502.01709","title":"Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2508.12292","title":"HuBERT-VIC: Improving Noise-Robust Automatic Speech Recognition of Speech Foundation Model via Variance-Invariance-Covariance Regularization","created":"2025-08-17","cited_by_count":2,"area":null},{"id":"2509.16031","title":"GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition","created":"2025-09-19","cited_by_count":2,"area":null},{"id":"2601.18396","title":"Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2303.12187","title":"Practice of the conformer enhanced AUDIO-VISUAL HUBERT on Mandarin and English","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2305.19972","title":"VILAS: Exploring the Effects of Vision and Language Context in Automatic Speech Recognition","created":"2023-05-31","cited_by_count":1,"area":null},{"id":"2502.05766","title":"Audio-Visual Representation Learning via Knowledge Distillation from Speech Foundation Models","created":"2025-02-09","cited_by_count":1,"area":"distill"},{"id":"2503.13371","title":"SyncDiff: Diffusion-based Talking Head Synthesis with Bottlenecked Temporal Visual Prior for Improved Synchronization","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2506.04635","title":"ViCocktail: Automated Multi-Modal Data Collection for Vietnamese Audio-Visual Speech Recognition","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2508.18734","title":"Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2509.17523","title":"Leveraging Audio-Visual Data to Reduce the Multilingual Gap in Self-Supervised Speech Models","created":"2025-09-22","cited_by_count":1,"area":null},{"id":"2512.15707","title":"GateFusion: Hierarchical Gated Cross-Modal Fusion for Active Speaker Detection","created":"2025-12-17","cited_by_count":1,"area":null},{"id":"2602.19316","title":"Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition","created":"2026-02-22","cited_by_count":1,"area":null},{"id":"2211.02133","title":"Streaming Audio-Visual Speech Recognition with Alignment Regularization","created":"2022-11-03","cited_by_count":0,"area":null},{"id":"2405.14709","title":"OpFlowTalker: Realistic and Natural Talking Face Generation via Optical Flow Guidance","created":"2024-05-23","cited_by_count":0,"area":null},{"id":"2409.19575","title":"Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective","created":"2024-09-29","cited_by_count":0,"area":null},{"id":"2603.08249","title":"Bootstrapping Audiovisual Speech Recognition in Zero-AV-Resource Scenarios","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2606.29632","title":"VIB-AVSR: Variational Information Bottleneck for Noise-Robust LLM-Based Audio-Visual Speech Recognition","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2609.10366","title":"AVSRBench: A Multi-Condition AVSR Benchmark","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.10394","title":"Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.18009","title":"SG-Mamba: Sparse Graph-Guided Mamba for Audio-Visual Speech Enhancement","created":"2026-09-16","cited_by_count":0,"area":"ssm"},{"id":"2609.20839","title":"Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2610.19559","title":"Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}