{"total":92,"rows":[{"id":"2204.08376","title":"Detecting Deepfakes with Self-Blended Images","created":"2022-04-18","cited_by_count":338,"area":null},{"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":"2201.07131","title":"Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection","created":"2022-01-18","cited_by_count":130,"area":null},{"id":"2101.03149","title":"VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency","created":"2021-01-08","cited_by_count":114,"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":"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":"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":"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":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"area":null},{"id":"2402.12636","title":"StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing","created":"2024-02-20","cited_by_count":21,"area":null},{"id":"2503.11315","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","created":"2025-03-14","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":"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":"2201.02143","title":"Classification of Long Sequential Data using Circular Dilated Convolutional Neural Networks","created":"2022-01-06","cited_by_count":13,"area":null},{"id":"2407.10575","title":"A Survey of Defenses Against AI-Generated Visual Media: Detection,Disruption, and Authentication","created":"2024-07-15","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":"2107.12600","title":"PiSLTRc: Position-informed Sign Language Transformer with Content-aware Convolution","created":"2021-07-27","cited_by_count":11,"area":null},{"id":"2305.03713","title":"Avatar Fingerprinting for Authorized Use of Synthetic Talking-Head Videos","created":"2023-05-05","cited_by_count":11,"area":null},{"id":"2403.14402","title":"XLAVS-R: Cross-Lingual Audio-Visual Speech Representation Learning for Noise-Robust Speech Perception","created":"2024-03-21","cited_by_count":11,"area":null},{"id":"2112.04748","title":"LipSound2: Self-Supervised Pre-Training for Lip-to-Speech Reconstruction and Lip Reading","created":"2021-12-09","cited_by_count":10,"area":null},{"id":"2211.09363","title":"Generalizable Deepfake Detection with Phase-Based Motion Analysis","created":"2022-11-17","cited_by_count":10,"area":null},{"id":"2212.10744","title":"An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits","created":"2022-12-21","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":"2202.13403","title":"A Multimodal German Dataset for Automatic Lip Reading Systems and Transfer Learning","created":"2022-02-27","cited_by_count":8,"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":"2310.13103","title":"AVTENet: A Human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection","created":"2023-10-19","cited_by_count":8,"area":null},{"id":"2108.13630","title":"SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory","created":"2021-08-31","cited_by_count":7,"area":null},{"id":"2408.11593","title":"MCDubber: Multimodal Context-Aware Expressive Video Dubbing","created":"2024-08-21","cited_by_count":7,"area":null},{"id":"2202.09081","title":"VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion","created":"2022-02-18","cited_by_count":6,"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":"2104.04784","title":"Lip reading using external viseme decoding","created":"2021-04-10","cited_by_count":5,"area":null},{"id":"2109.06692","title":"LRWR: Large-Scale Benchmark for Lip Reading in Russian language","created":"2021-09-14","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":"2302.05907","title":"LipLearner: Customizable Silent Speech Interactions on Mobile Devices","created":"2023-02-12","cited_by_count":5,"area":null},{"id":"2403.16071","title":"Landmark-Guided Cross-Speaker Lip Reading with Mutual Information Regularization","created":"2024-03-24","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":"2111.01740","title":"Personalized One-Shot Lipreading for an ALS Patient","created":"2021-11-02","cited_by_count":4,"area":null},{"id":"2204.02810","title":"Expression-preserving face frontalization improves visually assisted speech processing","created":"2022-04-06","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":"2501.04204","title":"LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognition","created":"2025-01-08","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":"2202.00538","title":"The impact of removing head movements on audio-visual speech enhancement","created":"2022-02-01","cited_by_count":3,"area":null},{"id":"2303.10770","title":"RN-Net: Reservoir Nodes-Enabled Neuromorphic Vision Sensing Network","created":"2023-03-19","cited_by_count":3,"area":null},{"id":"2305.03710","title":"Data Encoding For Healthcare Data Democratisation and Information Leakage Prevention","created":"2023-05-05","cited_by_count":3,"area":null},{"id":"2305.03711","title":"Medical records condensation: a roadmap towards healthcare data democratisation","created":"2023-05-05","cited_by_count":3,"area":null},{"id":"2308.08488","title":"Improving Audio-Visual Speech Recognition by Lip-Subword Correlation Based Visual Pre-training and Cross-Modal Fusion Encoder","created":"2023-08-14","cited_by_count":3,"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":"2404.11979","title":"MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2507.20568","title":"Learning Phonetic Context-Dependent Viseme for Enhancing Speech-Driven 3D Facial Animation","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2112.09060","title":"Towards Robust Real-time Audio-Visual Speech Enhancement","created":"2021-12-16","cited_by_count":2,"area":null},{"id":"2211.00988","title":"Audio-visual speech enhancement with a deep Kalman filter generative model","created":"2022-11-02","cited_by_count":2,"area":null},{"id":"2304.04068","title":"Word-level Persian Lipreading Dataset","created":"2023-04-08","cited_by_count":2,"area":null},{"id":"2305.14359","title":"Zero-shot personalized lip-to-speech synthesis with face image based voice control","created":"2023-05-09","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":"2505.04394","title":"SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2508.02000","title":"Localizing Audio-Visual Deepfakes via Hierarchical Boundary Modeling","created":"2025-08-04","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":"2111.09642","title":"Towards Intelligibility-Oriented Audio-Visual Speech Enhancement","created":"2021-11-18","cited_by_count":1,"area":null},{"id":"2305.12881","title":"Building an Invisible Shield for Your Portrait against Deepfakes","created":"2023-05-22","cited_by_count":1,"area":null},{"id":"2310.04858","title":"End-to-End Lip Reading in Romanian with Cross-Lingual Domain Adaptation and Lateral Inhibition","created":"2023-10-07","cited_by_count":1,"area":null},{"id":"2311.11549","title":"Unearthing Common Inconsistency for Generalisable Deepfake Detection","created":"2023-11-20","cited_by_count":1,"area":null},{"id":"2402.11520","title":"Cross-Attention Fusion of Visual and Geometric Features for Large Vocabulary Arabic Lipreading","created":"2024-02-18","cited_by_count":1,"area":null},{"id":"2403.02112","title":"A New Perspective on Smiling and Laughter Detection: Intensity Levels Matter","created":"2024-03-04","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":"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":"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":"2104.08510","title":"Exploring Deep Learning for Joint Audio-Visual Lip Biometrics","created":"2021-04-17","cited_by_count":0,"area":null},{"id":"2203.02655","title":"Audio-visual speech separation based on joint feature representation with cross-modal attention","created":"2022-03-05","cited_by_count":0,"area":null},{"id":"2211.10883","title":"Audio-visual video face hallucination with frequency supervision and cross modality support by speech based lip reading loss","created":"2022-11-20","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":"2506.07572","title":"Learning Speaker-Invariant Visual Features for Lipreading","created":"2025-06-09","cited_by_count":0,"area":null},{"id":"2506.16073","title":"TD3Net: A temporal densely connected multi-dilated convolutional network for lipreading","created":"2025-06-19","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":"2508.07233","title":"Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2508.17894","title":"Designing Practical Models for Isolated Word Visual Speech Recognition","created":"2025-08-25","cited_by_count":0,"area":null},{"id":"2510.22716","title":"LRW-Persian: Lip-reading in the Wild Dataset for Persian Language","created":"2025-10-26","cited_by_count":0,"area":null},{"id":"2510.26825","title":"Audio-Visual Speech Enhancement In Complex Scenarios With Separation And Dereverberation Joint Modeling","created":"2025-10-29","cited_by_count":0,"area":null},{"id":"2512.05126","title":"SyncVoice: Simple and Effective Automatic Video Dubbing with Vision-Augmented TTS","created":"2025-11-23","cited_by_count":0,"area":null},{"id":"2603.21808","title":"Cascade-Free Mandarin Visual Speech Recognition via Semantic-Guided Cross-Representation Alignment","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2607.08112","title":"VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness","created":"2026-07-09","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}