{"total":793,"rows":[{"id":"2110.13900","title":"WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing","created":"2021-10-26","cited_by_count":1657,"area":null},{"id":"2110.07058","title":"Ego4D: Around the World in 3,000 Hours of Egocentric Video","created":"2021-10-13","cited_by_count":1556,"area":null},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2104.11116","title":"Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation","created":"2021-04-22","cited_by_count":288,"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":"2112.02418","title":"YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone","created":"2021-12-04","cited_by_count":278,"area":null},{"id":"2204.11312","title":"EMOCA: Emotion Driven Monocular Face Capture and Animation","created":"2022-04-24","cited_by_count":255,"area":null},{"id":"2207.12393","title":"CelebV-HQ: A Large-Scale Video Facial Attributes Dataset","created":"2022-07-25","cited_by_count":250,"area":null},{"id":"2104.00355","title":"Speech Resynthesis from Discrete Disentangled Self-Supervised Representations","created":"2021-04-01","cited_by_count":243,"area":null},{"id":"2404.10667","title":"VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time","created":"2024-04-16","cited_by_count":187,"area":null},{"id":"2108.05080","title":"FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset","created":"2021-08-11","cited_by_count":181,"area":null},{"id":"2205.03409","title":"VFHQ: A High-Quality Dataset and Benchmark for Video Face Super-Resolution","created":"2022-05-06","cited_by_count":176,"area":null},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175,"area":null},{"id":"2204.06607","title":"Towards Metrical Reconstruction of Human Faces","created":"2022-04-13","cited_by_count":166,"area":null},{"id":"2109.00537","title":"ASVspoof 2021: accelerating progress in spoofed and deepfake speech detection","created":"2021-09-01","cited_by_count":161,"area":null},{"id":"2207.07621","title":"MegaPortraits: One-shot Megapixel Neural Head Avatars","created":"2022-07-15","cited_by_count":131,"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":"2103.05630","title":"ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis","created":"2021-03-09","cited_by_count":126,"area":null},{"id":"2112.08352","title":"Textless Speech-to-Speech Translation on Real Data","created":"2021-12-15","cited_by_count":121,"area":null},{"id":"2206.08343","title":"Realistic One-shot Mesh-based Head Avatars","created":"2022-06-16","cited_by_count":119,"area":null},{"id":"2210.15809","title":"Coverage-centric Coreset Selection for High Pruning Rates","created":"2022-10-28","cited_by_count":117,"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":"2303.14307","title":"Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels","created":"2023-03-25","cited_by_count":114,"area":null},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113,"area":null},{"id":"2303.14717","title":"CelebV-Text: A Large-Scale Facial Text-Video Dataset","created":"2023-03-26","cited_by_count":104,"area":null},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"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":"2401.08503","title":"Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis","created":"2024-01-16","cited_by_count":97,"area":null},{"id":"2211.14506","title":"Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis","created":"2022-11-26","cited_by_count":93,"area":null},{"id":"2305.05445","title":"StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator","created":"2023-05-09","cited_by_count":89,"area":null},{"id":"2112.02749","title":"One-shot Talking Face Generation from Single-speaker Audio-Visual Correlation Learning","created":"2021-12-06","cited_by_count":87,"area":null},{"id":"2410.03751","title":"Recent Advances in Speech Language Models: A Survey","created":"2024-10-01","cited_by_count":87,"area":null},{"id":"2207.00419","title":"Self-Supervised Learning for Videos: A Survey","created":"2022-06-18","cited_by_count":85,"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":"2409.09305","title":"The T05 System for The VoiceMOS Challenge 2024: Transfer Learning from Deep Image Classifier to Naturalness MOS Prediction of High-Quality Synthetic Speech","created":"2024-09-14","cited_by_count":83,"area":null},{"id":"2309.04946","title":"Efficient Emotional Adaptation for Audio-Driven Talking-Head Generation","created":"2023-09-10","cited_by_count":81,"area":null},{"id":"2311.15308","title":"AV-Deepfake1M: A Large-Scale LLM-Driven Audio-Visual Deepfake Dataset","created":"2023-11-26","cited_by_count":80,"area":null},{"id":"2404.01647","title":"EDTalk: Efficient Disentanglement for Emotional Talking Head Synthesis","created":"2024-04-02","cited_by_count":80,"area":null},{"id":"2201.01763","title":"Robust Self-Supervised Audio-Visual Speech Recognition","created":"2022-01-05","cited_by_count":75,"area":null},{"id":"2411.16331","title":"Sonic: Shifting Focus to Global Audio Perception in Portrait Animation","created":"2024-11-25","cited_by_count":72,"area":null},{"id":"2212.08062","title":"MetaPortrait: Identity-Preserving Talking Head Generation with Fast Personalized Adaptation","created":"2022-12-15","cited_by_count":69,"area":null},{"id":"2304.05097","title":"One-Shot High-Fidelity Talking-Head Synthesis with Deformable Neural Radiance Field","created":"2023-04-11","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":"2404.19110","title":"EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars","created":"2024-04-29","cited_by_count":66,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2403.13570","title":"Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer","created":"2024-03-20","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":"2307.09906","title":"Implicit Identity Representation Conditioned Memory Compensation Network for Talking Head video Generation","created":"2023-07-19","cited_by_count":61,"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":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59,"area":null},{"id":"2102.03247","title":"GaitSet: Cross-view Gait Recognition through Utilizing Gait as a Deep Set","created":"2021-02-05","cited_by_count":57,"area":null},{"id":"2211.06627","title":"MARLIN: Masked Autoencoder for facial video Representation LearnINg","created":"2022-11-12","cited_by_count":57,"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":"2211.15058","title":"Mix and Localize: Localizing Sound Sources in Mixtures","created":"2022-11-28","cited_by_count":54,"area":null},{"id":"2203.13441","title":"3D GAN Inversion for Controllable Portrait Image Animation","created":"2022-03-25","cited_by_count":53,"area":null},{"id":"2307.03441","title":"NOFA: NeRF-based One-shot Facial Avatar Reconstruction","created":"2023-07-07","cited_by_count":53,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2203.08488","title":"Pushing the limits of raw waveform speaker recognition","created":"2022-03-16","cited_by_count":51,"area":null},{"id":"2211.09809","title":"SPACE: Speech-driven Portrait Animation with Controllable Expression","created":"2022-11-17","cited_by_count":49,"area":null},{"id":"2307.10797","title":"HyperReenact: One-Shot Reenactment via Jointly Learning to Refine and Retarget Faces","created":"2023-07-20","cited_by_count":48,"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":"2109.00648","title":"The VoicePrivacy 2020 Challenge: Results and findings","created":"2021-09-01","cited_by_count":46,"area":null},{"id":"2203.02195","title":"Voice-Face Homogeneity Tells Deepfake","created":"2022-03-04","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":"2204.03083","title":"Audio-Visual Person-of-Interest DeepFake Detection","created":"2022-04-06","cited_by_count":43,"area":null},{"id":"2205.01155","title":"Emotion-Controllable Generalized Talking Face Generation","created":"2022-05-02","cited_by_count":43,"area":null},{"id":"2305.01979","title":"Glitch in the Matrix: A Large Scale Benchmark for Content Driven Audio-Visual Forgery Detection and Localization","created":"2023-05-03","cited_by_count":43,"area":null},{"id":"2307.02227","title":"MAE-DFER: Efficient Masked Autoencoder for Self-supervised Dynamic Facial Expression Recognition","created":"2023-07-05","cited_by_count":43,"area":null},{"id":"2311.15230","title":"GAIA: Zero-shot Talking Avatar Generation","created":"2023-11-26","cited_by_count":43,"area":null},{"id":"2304.10168","title":"High-Fidelity and Freely Controllable Talking Head Video Generation","created":"2023-04-20","cited_by_count":42,"area":null},{"id":"2401.15859","title":"Diffusion Facial Forgery Detection","created":"2024-01-29","cited_by_count":41,"area":null},{"id":"2404.02677","title":"The VoicePrivacy 2024 Challenge Evaluation Plan","created":"2024-04-03","cited_by_count":41,"area":null},{"id":"2208.11761","title":"IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages","created":"2022-08-24","cited_by_count":40,"area":null},{"id":"2109.15053","title":"Fine-tuning wav2vec2 for speaker recognition","created":"2021-09-30","cited_by_count":39,"area":null},{"id":"2203.15926","title":"Disentangled3D: Learning a 3D Generative Model with Disentangled Geometry and Appearance from Monocular Images","created":"2022-03-29","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":"2209.13514","title":"StyleSwap: Style-Based Generator Empowers Robust Face Swapping","created":"2022-09-27","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":"2505.15957","title":"Towards Holistic Evaluation of Large Audio-Language Models: A Comprehensive Survey","created":"2025-05-21","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":"2305.02572","title":"High-fidelity Generalized Emotional Talking Face Generation with Multi-modal Emotion Space Learning","created":"2023-05-04","cited_by_count":37,"area":null},{"id":"2101.03682","title":"MAAS: Multi-modal Assignation for Active Speaker Detection","created":"2021-01-11","cited_by_count":36,"area":null},{"id":"2104.02128","title":"End-to-End Speaker-Attributed ASR with Transformer","created":"2021-04-05","cited_by_count":35,"area":null},{"id":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35,"area":null},{"id":"2311.12454","title":"HierSpeech++: Bridging the Gap between Semantic and Acoustic Representation of Speech by Hierarchical Variational Inference for Zero-shot Speech Synthesis","created":"2023-11-21","cited_by_count":35,"area":null},{"id":"2212.04970","title":"Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers","created":"2022-12-09","cited_by_count":33,"area":null},{"id":"2104.14557","title":"Learned Spatial Representations for Few-shot Talking-Head Synthesis","created":"2021-04-29","cited_by_count":32,"area":null},{"id":"2109.02993","title":"Evaluation of an Audio-Video Multimodal Deepfake Dataset using Unimodal and Multimodal Detectors","created":"2021-09-07","cited_by_count":32,"area":null},{"id":"2304.00334","title":"TalkCLIP: Talking Head Generation with Text-Guided Expressive Speaking Styles","created":"2023-04-01","cited_by_count":32,"area":null},{"id":"2104.03493","title":"Riggable 3D Face Reconstruction via In-Network Optimization","created":"2021-04-08","cited_by_count":31,"area":null},{"id":"2106.03932","title":"How to Design a Three-Stage Architecture for Audio-Visual Active Speaker Detection in the Wild","created":"2021-06-07","cited_by_count":31,"area":null},{"id":"2107.04174","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","created":"2021-07-09","cited_by_count":31,"area":null},{"id":"2101.09866","title":"Supervision by Registration and Triangulation for Landmark Detection","created":"2021-01-25","cited_by_count":30,"area":null},{"id":"2401.05698","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","created":"2024-01-11","cited_by_count":30,"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":"2108.02607","title":"UniCon: Unified Context Network for Robust Active Speaker Detection","created":"2021-08-05","cited_by_count":28,"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":"2406.14272","title":"MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset","created":"2024-06-20","cited_by_count":28,"area":null}],"next_cursor":"100"}