{"total":274,"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":"2301.13430","title":"GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis","created":"2023-01-31","cited_by_count":131,"area":null},{"id":"2406.13495","title":"DF40: Toward Next-Generation Deepfake Detection","created":"2024-06-19","cited_by_count":129,"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":"2305.08293","title":"Identity-Preserving Talking Face Generation with Landmark and Appearance Priors","created":"2023-05-15","cited_by_count":98,"area":null},{"id":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98,"area":null},{"id":"2401.16423","title":"Synchformer: Efficient Synchronization from Sparse Cues","created":"2024-01-29","cited_by_count":97,"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":"2404.04104","title":"SMIRK: 3D Facial Expressions through Analysis-by-Neural-Synthesis","created":"2024-04-05","cited_by_count":84,"area":null},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75,"area":null},{"id":"2306.10799","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","created":"2023-06-19","cited_by_count":68,"area":null},{"id":"2112.13548","title":"Responsive Listening Head Generation: A Benchmark Dataset and Baseline","created":"2021-12-27","cited_by_count":67,"area":null},{"id":"2403.17881","title":"Deepfake Generation and Detection: A Benchmark and Survey","created":"2024-03-26","cited_by_count":67,"area":null},{"id":"2307.00162","title":"What Do Self-Supervised Speech Models Know About Words?","created":"2023-06-30","cited_by_count":64,"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":"2406.02951","title":"AVFF: Audio-Visual Feature Fusion for Video Deepfake Detection","created":"2024-06-05","cited_by_count":59,"area":null},{"id":"2111.00203","title":"Imitating Arbitrary Talking Style for Realistic Audio-DrivenTalking Face Synthesis","created":"2021-10-30","cited_by_count":56,"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":"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":"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":"2111.10592","title":"Deep Spoken Keyword Spotting: An Overview","created":"2021-11-20","cited_by_count":43,"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":"2305.00787","title":"GeneFace++: Generalized and Stable Real-Time Audio-Driven 3D Talking Face Generation","created":"2023-05-01","cited_by_count":42,"area":null},{"id":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40,"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":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35,"area":null},{"id":"2108.03256","title":"The Right to Talk: An Audio-Visual Transformer Approach","created":"2021-08-06","cited_by_count":33,"area":null},{"id":"2401.15668","title":"Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes","created":"2024-01-28","cited_by_count":32,"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":"2507.09862","title":"SpeakerVid-5M: A Large-Scale High-Quality Dataset for Audio-Visual Dyadic Interactive Human Generation","created":"2025-07-14","cited_by_count":30,"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":"2104.02775","title":"Looking into Your Speech: Learning Cross-modal Affinity for Audio-visual Speech Separation","created":"2021-03-25","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":"2210.07055","title":"Sparse in Space and Time: Audio-visual Synchronisation with Trainable Selectors","created":"2022-10-13","cited_by_count":26,"area":null},{"id":"2312.05430","title":"FT2TF: First-Person Statement Text-To-Talking Face Generation","created":"2023-12-09","cited_by_count":26,"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":"2503.13709","title":"Multi-modal Time Series Analysis: A Tutorial and Survey","created":"2025-03-17","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":"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":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"area":null},{"id":"2302.08841","title":"Lip-to-Speech Synthesis in the Wild with Multi-task Learning","created":"2023-02-17","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":"2405.10272","title":"Faces that Speak: Jointly Synthesising Talking Face and Speech from Text","created":"2024-05-16","cited_by_count":21,"area":null},{"id":"2203.02216","title":"Look\\&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement","created":"2022-03-04","cited_by_count":20,"area":null},{"id":"2309.10787","title":"AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models","created":"2023-09-19","cited_by_count":19,"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":"2506.10412","title":"Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series","created":"2025-06-12","cited_by_count":19,"area":null},{"id":"2508.19320","title":"MIDAS: Multimodal Interactive Digital-humAn Synthesis via Real-time Autoregressive Video Generation","created":"2025-08-26","cited_by_count":19,"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":"2109.02081","title":"Deep Person Generation: A Survey from the Perspective of Face, Pose and Cloth Synthesis","created":"2021-09-05","cited_by_count":16,"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":"2311.18168","title":"Probabilistic Speech-Driven 3D Facial Motion Synthesis: New Benchmarks, Methods, and Applications","created":"2023-11-30","cited_by_count":15,"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":"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":"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":"2502.10982","title":"TEASER: Token Enhanced Spatial Modeling for Expressions Reconstruction","created":"2025-02-16","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":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","cited_by_count":12,"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":"2205.04152","title":"Scaling up sign spotting through sign language dictionaries","created":"2022-05-09","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":"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":"2411.10193","title":"DiMoDif: Discourse Modality-information Differentiation for Audio-visual Deepfake Detection and Localization","created":"2024-11-15","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":"2308.01831","title":"Textless Unit-to-Unit training for Many-to-Many Multilingual Speech-to-Speech Translation","created":"2023-08-03","cited_by_count":11,"area":null},{"id":"2308.08143","title":"IIANet: An Intra- and Inter-Modality Attention Network for Audio-Visual Speech Separation","created":"2023-08-16","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":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","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":"2503.20308","title":"Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics","created":"2025-03-26","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":"2302.10915","title":"Conformers are All You Need for Visual Speech Recognition","created":"2023-02-17","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":"2311.14063","title":"Do VSR Models Generalize Beyond LRS3?","created":"2023-11-23","cited_by_count":9,"area":null},{"id":"2503.06273","title":"Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations","created":"2025-03-08","cited_by_count":9,"area":null},{"id":"2503.16956","title":"From Faces to Voices: Learning Hierarchical Representations for High-quality Video-to-Speech","created":"2025-03-21","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":"2212.06972","title":"Disentangling Prosody Representations with Unsupervised Speech Reconstruction","created":"2022-12-14","cited_by_count":8,"area":null},{"id":"2212.11377","title":"ReVISE: Self-Supervised Speech Resynthesis with Visual Input for Universal and Generalized Speech Enhancement","created":"2022-12-21","cited_by_count":8,"area":null},{"id":"2303.09797","title":"MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation","created":"2023-03-17","cited_by_count":8,"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":"2309.09470","title":"Face-Driven Zero-Shot Voice Conversion with Memory-based Face-Voice Alignment","created":"2023-09-18","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":"2410.05301","title":"Diffusion-based Unsupervised Audio-visual Speech Enhancement","created":"2024-10-04","cited_by_count":8,"area":null},{"id":"2507.20579","title":"AV-Deepfake1M++: A Large-Scale Audio-Visual Deepfake Benchmark with Real-World Perturbations","created":"2025-07-28","cited_by_count":8,"area":null},{"id":"2203.03984","title":"Attention-Based Lip Audio-Visual Synthesis for Talking Face Generation in the Wild","created":"2022-03-08","cited_by_count":7,"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":"2306.11541","title":"Audio-Driven 3D Facial Animation from In-the-Wild Videos","created":"2023-06-20","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":"2311.12457","title":"LIP-RTVE: An Audiovisual Database for Continuous Spanish in the Wild","created":"2023-11-21","cited_by_count":7,"area":null}],"next_cursor":"100"}