{"total":30,"rows":[{"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":"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":"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":"2208.04498","title":"Speaker-adaptive Lip Reading with User-dependent Padding","created":"2022-08-09","cited_by_count":17,"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":"2504.02386","title":"VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models","created":"2025-04-03","cited_by_count":11,"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":"2211.10999","title":"LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoders","created":"2022-11-20","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":"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":"2503.22265","title":"DeepAudio-V1:Towards Multi-Modal Multi-Stage End-to-End Video to Speech and Audio Generation","created":"2025-03-28","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":"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":"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":"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":"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":"2501.18157","title":"Efficient Audiovisual Speech Processing via MUTUD: Multimodal Training and Unimodal Deployment","created":"2025-01-30","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":"2409.19575","title":"Quantitative Analysis of Audio-Visual Tasks: An Information-Theoretic Perspective","created":"2024-09-29","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":"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},{"id":"2610.01012","title":"Watch Your Speech: Text-aware Video-to-Speech Synthesis with Textual Conditioning","created":"2026-10-01","cited_by_count":0,"area":null}],"next_cursor":null}