{"total":732,"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":"2111.09296","title":"XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scale","created":"2021-11-17","cited_by_count":601,"area":null},{"id":"2106.04624","title":"SpeechBrain: A General-Purpose Speech Toolkit","created":"2021-06-08","cited_by_count":406,"area":null},{"id":"2211.12194","title":"SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation","created":"2022-11-22","cited_by_count":382,"area":null},{"id":"2410.19168","title":"MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark","created":"2024-10-24","cited_by_count":288,"area":"lr"},{"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":"2205.10643","title":"Self-Supervised Speech Representation Learning: A Review","created":"2022-05-21","cited_by_count":260,"area":null},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","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":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210,"area":null},{"id":"2407.03168","title":"LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control","created":"2024-07-03","cited_by_count":206,"area":null},{"id":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203,"area":null},{"id":"2201.02639","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","created":"2022-01-07","cited_by_count":184,"area":null},{"id":"2110.07205","title":"SpeechT5: Unified-Modal Encoder-Decoder Pre-Training for Spoken Language Processing","created":"2021-10-14","cited_by_count":180,"area":null},{"id":"2203.06605","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2022-03-13","cited_by_count":178,"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":"2203.04036","title":"StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN","created":"2022-03-08","cited_by_count":169,"area":null},{"id":"2104.15069","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","created":"2021-04-30","cited_by_count":163,"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":"2107.09293","title":"Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion","created":"2021-07-20","cited_by_count":149,"area":null},{"id":"2502.01061","title":"OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models","created":"2025-02-03","cited_by_count":129,"area":null},{"id":"2406.16020","title":"AudioBench: A Universal Benchmark for Audio Large Language Models","created":"2024-06-23","cited_by_count":128,"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":"2104.09770","title":"M2TR: Multi-modal Multi-scale Transformers for Deepfake Detection","created":"2021-04-20","cited_by_count":114,"area":null},{"id":"2404.00656","title":"WavLLM: Towards Robust and Adaptive Speech Large Language Model","created":"2024-03-31","cited_by_count":109,"area":null},{"id":"2103.06695","title":"BYOL for Audio: Self-Supervised Learning for General-Purpose Audio Representation","created":"2021-03-11","cited_by_count":106,"area":null},{"id":"2211.14758","title":"VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild","created":"2022-11-27","cited_by_count":106,"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":"2306.08990","title":"Emotional Speech-Driven Animation with Content-Emotion Disentanglement","created":"2023-06-15","cited_by_count":98,"area":null},{"id":"2408.08739","title":"ASVspoof 5: Crowdsourced Speech Data, Deepfakes, and Adversarial Attacks at Scale","created":"2024-08-16","cited_by_count":91,"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":"2109.13226","title":"BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition","created":"2021-09-27","cited_by_count":88,"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":"2310.19773","title":"MM-VID: Advancing Video Understanding with GPT-4V(ision)","created":"2023-10-30","cited_by_count":83,"area":null},{"id":"2111.02735","title":"A Fine-tuned Wav2vec 2.0/HuBERT Benchmark For Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding","created":"2021-11-04","cited_by_count":82,"area":null},{"id":"2103.10094","title":"KoDF: A Large-scale Korean DeepFake Detection Dataset","created":"2021-03-18","cited_by_count":80,"area":null},{"id":"2111.10367","title":"SLUE: New Benchmark Tasks for Spoken Language Understanding Evaluation on Natural Speech","created":"2021-11-19","cited_by_count":72,"area":null},{"id":"2101.08596","title":"LEAF: A Learnable Frontend for Audio Classification","created":"2021-01-21","cited_by_count":69,"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":"2403.17881","title":"Deepfake Generation and Detection: A Benchmark and Survey","created":"2024-03-26","cited_by_count":67,"area":null},{"id":"2405.03121","title":"AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding","created":"2024-05-06","cited_by_count":67,"area":null},{"id":"2203.01205","title":"Audio Self-supervised Learning: A Survey","created":"2022-03-02","cited_by_count":65,"area":null},{"id":"2602.06053","title":"PersonaPlex: Voice and Role Control for Full Duplex Conversational Speech Models","created":"2026-01-14","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":"2212.04248","title":"Talking Head Generation with Probabilistic Audio-to-Visual Diffusion Priors","created":"2022-12-07","cited_by_count":55,"area":"diffusion"},{"id":"2203.13441","title":"3D GAN Inversion for Controllable Portrait Image Animation","created":"2022-03-25","cited_by_count":53,"area":null},{"id":"2101.00387","title":"What all do audio transformer models hear? Probing Acoustic Representations for Language Delivery and its Structure","created":"2021-01-02","cited_by_count":52,"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":"2412.12093","title":"CAP4D: Creating Animatable 4D Portrait Avatars with Morphable Multi-View Diffusion Models","created":"2024-12-16","cited_by_count":52,"area":"diffusion"},{"id":"2203.08488","title":"Pushing the limits of raw waveform speaker recognition","created":"2022-03-16","cited_by_count":51,"area":null},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"area":null},{"id":"2507.02768","title":"DeSTA2.5-Audio: Toward General-Purpose Large Audio Language Model with Self-Generated Cross-Modal Alignment","created":"2025-07-03","cited_by_count":50,"area":"synth"},{"id":"2304.03199","title":"Face Animation with an Attribute-Guided Diffusion Model","created":"2023-04-06","cited_by_count":48,"area":"diffusion"},{"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":"2312.01841","title":"VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior","created":"2023-12-04","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":"2301.06281","title":"DPE: Disentanglement of Pose and Expression for General Video Portrait Editing","created":"2023-01-16","cited_by_count":46,"area":null},{"id":"2409.20007","title":"DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Data","created":"2024-09-30","cited_by_count":45,"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":"2112.04432","title":"Audio-Visual Synchronisation in the wild","created":"2021-12-08","cited_by_count":40,"area":null},{"id":"2203.16844","title":"Open Source MagicData-RAMC: A Rich Annotated Mandarin Conversational(RAMC) Speech Dataset","created":"2022-03-31","cited_by_count":40,"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":"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":"2212.02802","title":"Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding","created":"2022-12-06","cited_by_count":39,"area":null},{"id":"2106.13000","title":"QASR: QCRI Aljazeera Speech Resource -- A Large Scale Annotated Arabic Speech Corpus","created":"2021-06-24","cited_by_count":38,"area":null},{"id":"2208.05751","title":"FDNeRF: Few-shot Dynamic Neural Radiance Fields for Face Reconstruction and Expression Editing","created":"2022-08-11","cited_by_count":38,"area":null},{"id":"2405.11029","title":"Generative Artificial Intelligence: A Systematic Review and Applications","created":"2024-05-17","cited_by_count":37,"area":null},{"id":"2405.11831","title":"SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model","created":"2024-05-20","cited_by_count":37,"area":"ssm"},{"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":"2105.07142","title":"Move2Hear: Active Audio-Visual Source Separation","created":"2021-05-15","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":"2204.05018","title":"Structure-Aware Motion Transfer with Deformable Anchor Model","created":"2022-04-11","cited_by_count":34,"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":"2110.04621","title":"Universal Paralinguistic Speech Representations Using Self-Supervised Conformers","created":"2021-10-09","cited_by_count":32,"area":null},{"id":"2303.00733","title":"SpeechPrompt v2: Prompt Tuning for Speech Classification Tasks","created":"2023-03-01","cited_by_count":32,"area":null},{"id":"2406.14294","title":"DASB - Discrete Audio and Speech Benchmark","created":"2024-06-20","cited_by_count":32,"area":"mllm"},{"id":"2112.05907","title":"Smooth-Swap: A Simple Enhancement for Face-Swapping with Smoothness","created":"2021-12-11","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":"2112.10483","title":"Fusion and Orthogonal Projection for Improved Face-Voice Association","created":"2021-12-20","cited_by_count":29,"area":null},{"id":"2301.04474","title":"Speech Driven Video Editing via an Audio-Conditioned Diffusion Model","created":"2023-01-10","cited_by_count":28,"area":"diffusion"},{"id":"2306.00452","title":"Speech Self-Supervised Representation Benchmarking: Are We Doing it Right?","created":"2023-06-01","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},{"id":"2202.00046","title":"Finding Directions in GAN's Latent Space for Neural Face Reenactment","created":"2022-01-31","cited_by_count":27,"area":null},{"id":"2306.03000","title":"BeyondPixels: A Comprehensive Review of the Evolution of Neural Radiance Fields","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2311.00994","title":"LaughTalk: Expressive 3D Talking Head Generation with Laughter","created":"2023-11-02","cited_by_count":27,"area":null},{"id":"2106.07732","title":"Learning Audio-Visual Dereverberation","created":"2021-06-14","cited_by_count":26,"area":null},{"id":"2109.00471","title":"Sparse to Dense Motion Transfer for Face Image Animation","created":"2021-09-01","cited_by_count":25,"area":null},{"id":"2110.09714","title":"Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information","created":"2021-10-19","cited_by_count":25,"area":null},{"id":"2111.14448","title":"AVA-AVD: Audio-Visual Speaker Diarization in the Wild","created":"2021-11-29","cited_by_count":25,"area":null},{"id":"2203.14250","title":"End-to-End Active Speaker Detection","created":"2022-03-27","cited_by_count":25,"area":null},{"id":"2306.04186","title":"Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks","created":"2023-06-07","cited_by_count":25,"area":"distill"},{"id":"2311.06443","title":"CVTHead: One-shot Controllable Head Avatar with Vertex-feature Transformer","created":"2023-11-11","cited_by_count":24,"area":null},{"id":"2406.10735","title":"How Should We Extract Discrete Audio Tokens from Self-Supervised Models?","created":"2024-06-15","cited_by_count":24,"area":null}],"next_cursor":"100"}