{"total":79,"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":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114,"area":null},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95,"area":null},{"id":"2301.01767","title":"Self-Supervised Video Forensics by Audio-Visual Anomaly Detection","created":"2023-01-04","cited_by_count":85,"area":null},{"id":"2108.08258","title":"LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector","created":"2021-08-18","cited_by_count":70,"area":null},{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63,"area":null},{"id":"2104.10955","title":"Distilling Audio-Visual Knowledge by Compositional Contrastive Learning","created":"2021-04-22","cited_by_count":53,"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":"2106.09171","title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision","created":"2021-06-16","cited_by_count":44,"area":null},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40,"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":"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":"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":"2402.15151","title":"Where Visual Speech Meets Language: VSP-LLM Framework for Efficient and Context-Aware Visual Speech Processing","created":"2024-02-23","cited_by_count":30,"area":null},{"id":"2104.06401","title":"Self-supervised object detection from audio-visual correspondence","created":"2021-04-13","cited_by_count":29,"area":null},{"id":"2203.03598","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","created":"2022-03-07","cited_by_count":27,"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":"2301.01456","title":"Audio-Visual Efficient Conformer for Robust Speech Recognition","created":"2023-01-04","cited_by_count":22,"area":null},{"id":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"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":"2404.02098","title":"BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition","created":"2024-04-02","cited_by_count":21,"area":null},{"id":"2207.09966","title":"Temporal and cross-modal attention for audio-visual zero-shot learning","created":"2022-07-20","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":"2208.04498","title":"Speaker-adaptive Lip Reading with User-dependent Padding","created":"2022-08-09","cited_by_count":17,"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":"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":"2411.02256","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","created":"2024-11-04","cited_by_count":15,"area":null},{"id":"2302.08102","title":"Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition","created":"2023-02-16","cited_by_count":14,"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":"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":"2309.08535","title":"Visual Speech Recognition for Languages with Limited Labeled Data using Automatic Labels from Whisper","created":"2023-09-15","cited_by_count":13,"area":null},{"id":"2203.07996","title":"Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition","created":"2022-02-24","cited_by_count":12,"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":"2110.15957","title":"Visual Keyword Spotting with Attention","created":"2021-10-29","cited_by_count":11,"area":null},{"id":"2203.05683","title":"Deep Multimodal Guidance for Medical Image Classification","created":"2022-03-10","cited_by_count":11,"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":"2102.05645","title":"Automated Video Labelling: Identifying Faces by Corroborative Evidence","created":"2021-02-10","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":"2306.06410","title":"OpenSR: Open-Modality Speech Recognition via Maintaining Multi-Modality Alignment","created":"2023-06-10","cited_by_count":8,"area":null},{"id":"2401.09802","title":"Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2406.18864","title":"Learning Modality Knowledge Alignment for Cross-Modality Transfer","created":"2024-06-27","cited_by_count":8,"area":null},{"id":"2508.08237","title":"VGGSounder: Audio-Visual Evaluations for Foundation Models","created":"2025-08-11","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":"2307.04552","title":"SparseVSR: Lightweight and Noise Robust Visual Speech Recognition","created":"2023-07-10","cited_by_count":7,"area":null},{"id":"2507.18863","title":"Phoneme-Level Visual Speech Recognition via Point-Visual Fusion and Language Model Reconstruction","created":"2025-07-25","cited_by_count":7,"area":null},{"id":"2305.15403","title":"AV-TranSpeech: Audio-Visual Robust Speech-to-Speech Translation","created":"2023-05-24","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":"2104.04784","title":"Lip reading using external viseme decoding","created":"2021-04-10","cited_by_count":5,"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":"2110.07879","title":"Advances and Challenges in Deep Lip Reading","created":"2021-10-15","cited_by_count":4,"area":null},{"id":"2301.10180","title":"A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset","created":"2023-01-21","cited_by_count":4,"area":null},{"id":"2303.08670","title":"Deep Visual Forced Alignment: Learning to Align Transcription with Talking Face Video","created":"2023-02-27","cited_by_count":4,"area":null},{"id":"2303.11551","title":"ModEFormer: Modality-Preserving Embedding for Audio-Video Synchronization using Transformers","created":"2023-03-21","cited_by_count":4,"area":null},{"id":"2104.10299","title":"Voice2Mesh: Cross-Modal 3D Face Model Generation from Voices","created":"2021-04-21","cited_by_count":3,"area":null},{"id":"2206.02050","title":"Learning Speaker-specific Lip-to-Speech Generation","created":"2022-06-04","cited_by_count":3,"area":null},{"id":"2206.06424","title":"Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence","created":"2022-06-13","cited_by_count":3,"area":null},{"id":"2409.05564","title":"LEROjD: Lidar Extended Radar-Only Object Detection","created":"2024-09-09","cited_by_count":3,"area":null},{"id":"2307.10157","title":"Leveraging Visemes for Better Visual Speech Representation and Lip Reading","created":"2023-07-19","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":"2105.01517","title":"Where and When: Space-Time Attention for Audio-Visual Explanations","created":"2021-05-04","cited_by_count":1,"area":null},{"id":"2308.08125","title":"Radio2Text: Streaming Speech Recognition Using mmWave Radio Signals","created":"2023-08-16","cited_by_count":1,"area":null},{"id":"2309.03869","title":"Text-to-feature diffusion for audio-visual few-shot learning","created":"2023-09-07","cited_by_count":1,"area":null},{"id":"2505.03186","title":"CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization","created":"2025-05-06","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":"2108.10254","title":"Automatic Speech Recognition And Limited Vocabulary: A Survey","created":"2021-08-23","cited_by_count":0,"area":null},{"id":"2307.09006","title":"OxfordVGG Submission to the EGO4D AV Transcription Challenge","created":"2023-07-18","cited_by_count":0,"area":null},{"id":"2311.12480","title":"Speaker-Adapted End-to-End Visual Speech Recognition for Continuous Spanish","created":"2023-11-21","cited_by_count":0,"area":null},{"id":"2406.00495","title":"Audio-Visual Talker Localization in Video for Spatial Sound Reproduction","created":"2024-06-01","cited_by_count":0,"area":null},{"id":"2409.05307","title":"RAL:Redundancy-Aware Lipreading Model Based on Differential Learning with Symmetric Views","created":"2024-09-09","cited_by_count":0,"area":null},{"id":"2409.07210","title":"Enhancing CTC-Based Visual Speech Recognition","created":"2024-09-11","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":"2603.26064","title":"MuDD: A Multimodal Deception Detection Dataset and GSR-Guided Progressive Distillation for Non-Contact Deception Detection","created":"2026-03-27","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}