{"total":36,"rows":[{"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":"2205.02058","title":"SVTS: Scalable Video-to-Speech Synthesis","created":"2022-05-04","cited_by_count":35,"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":"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":"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":"2308.09311","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":"2302.08102","title":"Prompt Tuning of Deep Neural Networks for Speaker-adaptive Visual Speech Recognition","created":"2023-02-16","cited_by_count":14,"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":"2206.10421","title":"Rethinking Audio-visual Synchronization for Active Speaker Detection","created":"2022-06-21","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":"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":"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":"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":"2504.13386","title":"Supervising 3D Talking Head Avatars with Analysis-by-Audio-Synthesis","created":"2025-04-18","cited_by_count":5,"area":null},{"id":"2303.08670","title":"Deep Visual Forced Alignment: Learning to Align Transcription with Talking Face Video","created":"2023-02-27","cited_by_count":4,"area":null},{"id":"2305.19556","title":"Exploring Phonetic Context-Aware Lip-Sync For Talking Face Generation","created":"2023-05-31","cited_by_count":4,"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":"2510.23969","title":"emg2speech: Synthesizing speech from electromyography using self-supervised speech models","created":"2025-10-28","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":"2306.15451","title":"Advancing Adversarial Training by Injecting Booster Signal","created":"2023-06-27","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":"2407.19259","title":"Fine-Grained Scene Graph Generation via Sample-Level Bias Prediction","created":"2024-07-27","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":"2512.13904","title":"Generative AI for Video Translation: A Scalable Architecture for Multilingual Video Conferencing","created":"2025-12-15","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}