{"total":58,"rows":[{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287,"area":null},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151,"area":null},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75,"area":null},{"id":"2212.06246","title":"Jointly Learning Visual and Auditory Speech Representations from Raw Data","created":"2022-12-12","cited_by_count":47,"area":null},{"id":"2303.08536","title":"Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring","created":"2023-03-15","cited_by_count":42,"area":null},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41,"area":null},{"id":"2204.01725","title":"Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading","created":"2022-04-04","cited_by_count":39,"area":null},{"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":"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":"2201.10439","title":"Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video","created":"2022-01-25","cited_by_count":31,"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":"2207.06020","title":"Visual Context-driven Audio Feature Enhancement for Robust End-to-End Audio-Visual Speech Recognition","created":"2022-07-13","cited_by_count":24,"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":"2301.01456","title":"Audio-Visual Efficient Conformer for Robust Speech Recognition","created":"2023-01-04","cited_by_count":22,"area":null},{"id":"2303.17200","title":"SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision","created":"2023-03-30","cited_by_count":21,"area":null},{"id":"2308.12558","title":"Hyperbolic Audio-visual Zero-shot Learning","created":"2023-08-24","cited_by_count":19,"area":null},{"id":"2204.01265","title":"Multi-modality Associative Bridging through Memory: Speech Sound Recollected from Face Video","created":"2022-04-04","cited_by_count":18,"area":null},{"id":"2308.07593","title":"AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model","created":"2023-08-15","cited_by_count":16,"area":null},{"id":"2406.12233","title":"SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2403.04245","title":"A Study of Dropout-Induced Modality Bias on Robustness to Missing Video Frames for Audio-Visual Speech Recognition","created":"2024-03-07","cited_by_count":12,"area":null},{"id":"2503.21408","title":"VALLR: Visual ASR Language Model for Lip Reading","created":"2025-03-27","cited_by_count":11,"area":null},{"id":"2201.03804","title":"CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition","created":"2022-01-11","cited_by_count":10,"area":null},{"id":"2407.08130","title":"Spiking Tucker Fusion Transformer for Audio-Visual Zero-Shot Learning","created":"2024-07-11","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":"2302.02141","title":"LipFormer: Learning to Lipread Unseen Speakers based on Visual-Landmark Transformers","created":"2023-02-04","cited_by_count":9,"area":null},{"id":"2305.04542","title":"Multi-Temporal Lip-Audio Memory for Visual Speech Recognition","created":"2023-05-08","cited_by_count":9,"area":null},{"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":"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":"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":"2112.02834","title":"A Generalized Zero-Shot Quantization of Deep Convolutional Neural Networks via Learned Weights Statistics","created":"2021-12-06","cited_by_count":6,"area":null},{"id":"2312.09727","title":"LiteVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2109.09536","title":"Audio-Visual Speech Recognition is Worth 32$\\times$32$\\times$8 Voxels","created":"2021-09-20","cited_by_count":5,"area":null},{"id":"2205.14295","title":"Is Lip Region-of-Interest Sufficient for Lipreading?","created":"2022-05-28","cited_by_count":5,"area":null},{"id":"2209.09735","title":"Relaxed Attention for Transformer Models","created":"2022-09-20","cited_by_count":5,"area":null},{"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":"2110.07879","title":"Advances and Challenges in Deep Lip Reading","created":"2021-10-15","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":"2502.01547","title":"mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2308.08849","title":"A Survey on Deep Multi-modal Learning for Body Language Recognition and Generation","created":"2023-08-17","cited_by_count":3,"area":null},{"id":"2312.10088","title":"On Robustness to Missing Video for Audiovisual Speech Recognition","created":"2023-12-13","cited_by_count":3,"area":null},{"id":"2409.02266","title":"LSTMSE-Net: Long Short Term Speech Enhancement Network for Audio-visual Speech Enhancement","created":"2024-09-03","cited_by_count":3,"area":null},{"id":"2103.07595","title":"Learning Defense Transformers for Counterattacking Adversarial Examples","created":"2021-03-13","cited_by_count":2,"area":null},{"id":"2502.05758","title":"Target Speaker Lipreading by Audio-Visual Self-Distillation Pretraining and Speaker Adaptation","created":"2025-02-09","cited_by_count":2,"area":"distill"},{"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":"2108.03543","title":"Spatio-Temporal Attention Mechanism and Knowledge Distillation for Lip Reading","created":"2021-08-07","cited_by_count":1,"area":"distill"},{"id":"2207.05692","title":"Lip-Listening: Mixing Senses to Understand Lips using Cross Modality Knowledge Distillation for Word-Based Models","created":"2022-06-05","cited_by_count":1,"area":"distill"},{"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":"2406.04432","title":"LipGER: Visually-Conditioned Generative Error Correction for Robust Automatic Speech Recognition","created":"2024-06-06","cited_by_count":1,"area":null},{"id":"2501.18157","title":"Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment","created":"2025-01-30","cited_by_count":1,"area":null},{"id":"2508.07608","title":"AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2405.16235","title":"A better approach to diagnose retinal diseases: Combining our Segmentation-based Vascular Enhancement with deep learning features","created":"2024-05-25","cited_by_count":0,"area":null},{"id":"2409.19420","title":"Multi-sensor Learning Enables Information Transfer across Different Sensory Data and Augments Multi-modality Imaging","created":"2024-09-28","cited_by_count":0,"area":null},{"id":"2410.17394","title":"packetLSTM: Dynamic LSTM Framework for Streaming Data with Varying Feature Space","created":"2024-10-22","cited_by_count":0,"area":null},{"id":"2506.07572","title":"Learning Speaker-Invariant Visual Features for Lipreading","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2508.02460","title":"InfoSyncNet: Information Synchronization Temporal Convolutional Network for Visual Speech Recognition","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2601.12436","title":"Purification Before Fusion: Toward Mask-Free Speech Enhancement for Robust Audio-Visual Speech Recognition","created":"2026-01-18","cited_by_count":0,"area":null}],"next_cursor":null}