{"total":62,"rows":[{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367,"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":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2304.08490","title":"Conditional Generation of Audio from Video via Foley Analogies","created":"2023-04-17","cited_by_count":52,"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":"2110.08243","title":"Neural Dubber: Dubbing for Videos According to Scripts","created":"2021-10-15","cited_by_count":39,"area":null},{"id":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35,"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":"2104.13332","title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","created":"2021-04-27","cited_by_count":27,"area":null},{"id":"2203.17263","title":"Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis","created":"2022-03-31","cited_by_count":24,"area":null},{"id":"2203.01265","title":"Self-supervised Transformer for Deepfake Detection","created":"2022-03-02","cited_by_count":22,"area":null},{"id":"2205.05072","title":"Learning Visual Styles from Audio-Visual Associations","created":"2022-05-10","cited_by_count":22,"area":null},{"id":"2210.02884","title":"Vision+X: A Survey on Multimodal Learning in the Light of Data","created":"2022-10-05","cited_by_count":22,"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":"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":"2110.03342","title":"VisualTTS: TTS with Accurate Lip-Speech Synchronization for Automatic Voice Over","created":"2021-10-07","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":"2308.15256","title":"Let There Be Sound: Reconstructing High Quality Speech from Silent Videos","created":"2023-08-29","cited_by_count":12,"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":"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":"2207.03800","title":"FastLTS: Non-Autoregressive End-to-End Unconstrained Lip-to-Speech Synthesis","created":"2022-07-08","cited_by_count":8,"area":null},{"id":"2209.00642","title":"Lip-to-Speech Synthesis for Arbitrary Speakers in the Wild","created":"2022-09-01","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":"2409.14340","title":"Self-Supervised Audio-Visual Soundscape Stylization","created":"2024-09-22","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":"2403.01087","title":"Towards Accurate Lip-to-Speech Synthesis in-the-Wild","created":"2024-03-02","cited_by_count":7,"area":null},{"id":"2404.12725","title":"Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction","created":"2024-04-19","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":"2206.07458","title":"VisageSynTalk: Unseen Speaker Video-to-Speech Synthesis via Speech-Visage Feature Selection","created":"2022-06-15","cited_by_count":6,"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":"2504.13386","title":"Supervising 3D Talking Head Avatars with Analysis-by-Audio-Synthesis","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2107.12003","title":"Facetron: A Multi-speaker Face-to-Speech Model based on Cross-modal Latent Representations","created":"2021-07-26","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":"2306.17005","title":"High-Quality Automatic Voice Over with Accurate Alignment: Supervision through Self-Supervised Discrete Speech Units","created":"2023-06-29","cited_by_count":4,"area":null},{"id":"2502.12489","title":"A Comprehensive Survey on Generative AI for Video-to-Music Generation","created":"2025-02-18","cited_by_count":4,"area":null},{"id":"2206.02050","title":"Learning Speaker-specific Lip-to-Speech Generation","created":"2022-06-04","cited_by_count":3,"area":null},{"id":"2306.15464","title":"Large-scale unsupervised audio pre-training for video-to-speech synthesis","created":"2023-06-27","cited_by_count":3,"area":null},{"id":"2502.12002","title":"NaturalL2S: End-to-End High-quality Multispeaker Lip-to-Speech Synthesis with Differential Digital Signal Processing","created":"2025-02-17","cited_by_count":3,"area":null},{"id":"2506.04214","title":"Sounding that Object: Interactive Object-Aware Image to Audio Generation","created":"2025-06-04","cited_by_count":3,"area":null},{"id":"2510.23969","title":"emg2speech: Synthesizing speech from electromyography using self-supervised speech models","created":"2025-10-28","cited_by_count":3,"area":null},{"id":"2601.14777","title":"FunCineForge: A Unified Dataset Toolkit and Model for Zero-Shot Movie Dubbing in Diverse Cinematic Scenes","created":"2026-01-21","cited_by_count":3,"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":"2309.11338","title":"TRAVID: An End-to-End Video Translation Framework","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2411.17690","title":"Mechanisms of Multimodal Synchronization: Insights from Decoder-Based Video-Text-to-Speech Synthesis","created":"2024-11-26","cited_by_count":2,"area":null},{"id":"2207.04213","title":"Dual-Path Cross-Modal Attention for better Audio-Visual Speech Extraction","created":"2022-07-09","cited_by_count":1,"area":null},{"id":"2208.10489","title":"Audio Deepfake Attribution: An Initial Dataset and Investigation","created":"2022-08-21","cited_by_count":1,"area":null},{"id":"2302.13838","title":"Cross-modal Face- and Voice-style Transfer","created":"2023-02-27","cited_by_count":1,"area":null},{"id":"2303.00502","title":"On the Audio-visual Synchronization for Lip-to-Speech Synthesis","created":"2023-03-01","cited_by_count":1,"area":null},{"id":"2307.01233","title":"RobustL2S: Speaker-Specific Lip-to-Speech Synthesis exploiting Self-Supervised Representations","created":"2023-07-03","cited_by_count":1,"area":null},{"id":"2307.16584","title":"Audio-visual video-to-speech synthesis with synthesized input audio","created":"2023-07-31","cited_by_count":1,"area":null},{"id":"2407.18541","title":"Towards Improving NAM-to-Speech Synthesis Intelligibility using Self-Supervised Speech Models","created":"2024-07-26","cited_by_count":1,"area":null},{"id":"2503.05223","title":"DiVISe: Direct Visual-Input Speech Synthesis Preserving Speaker Characteristics And Intelligibility","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2503.14928","title":"Shushing! Let's Imagine an Authentic Speech from the Silent Video","created":"2025-03-19","cited_by_count":1,"area":null},{"id":"2505.22024","title":"RESOUND: Speech Reconstruction from Silent Videos via Acoustic-Semantic Decomposed Modeling","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2206.14009","title":"Show Me Your Face, And I'll Tell You How You Speak","created":"2022-06-28","cited_by_count":0,"area":null},{"id":"2503.06588","title":"Speech Audio Generation from dynamic MRI via a Knowledge Enhanced Conditional Variational Autoencoder","created":"2025-03-09","cited_by_count":0,"area":null},{"id":"2507.00498","title":"MuteSwap: Visual-informed Silent Video Identity Conversion","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2604.15923","title":"Hierarchical Codec Diffusion for Video-to-Speech Generation","created":"2026-04-17","cited_by_count":0,"area":null},{"id":"2606.09667","title":"Cross-Modal Masking for Robust Silent Speech Synthesis Using sEMG and Lipreading","created":"2026-06-08","cited_by_count":0,"area":null}],"next_cursor":null}