{"total":23,"rows":[{"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":"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":"2212.04054","title":"Learning to Dub Movies via Hierarchical Prosody Models","created":"2022-12-08","cited_by_count":29,"area":null},{"id":"2406.12233","title":"SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization","created":"2024-06-18","cited_by_count":14,"area":null},{"id":"2305.04542","title":"Multi-Temporal Lip-Audio Memory for Visual Speech Recognition","created":"2023-05-08","cited_by_count":9,"area":null},{"id":"2311.14063","title":"Do VSR Models Generalize Beyond LRS3?","created":"2023-11-23","cited_by_count":9,"area":null},{"id":"2401.09802","title":"Efficient Training for Multilingual Visual Speech Recognition: Pre-training with Discretized Visual Speech Representation","created":"2024-01-18","cited_by_count":8,"area":null},{"id":"2301.10180","title":"A Multi-Purpose Audio-Visual Corpus for Multi-Modal Persian Speech Recognition: the Arman-AV Dataset","created":"2023-01-21","cited_by_count":4,"area":null},{"id":"2501.04204","title":"LipGen: Viseme-Guided Lip Video Generation for Enhancing Visual Speech Recognition","created":"2025-01-08","cited_by_count":4,"area":null},{"id":"2501.13375","title":"Bridging The Multi-Modality Gaps of Audio, Visual and Linguistic for Speech Enhancement","created":"2025-01-23","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":"2310.05058","title":"Learning Separable Hidden Unit Contributions for Speaker-Adaptive Lip-Reading","created":"2023-10-08","cited_by_count":2,"area":null},{"id":"2505.04394","title":"SwinLip: An Efficient Visual Speech Encoder for Lip Reading Using Swin Transformer","created":"2025-05-07","cited_by_count":2,"area":null},{"id":"2310.04858","title":"End-to-End Lip Reading in Romanian with Cross-Lingual Domain Adaptation and Lateral Inhibition","created":"2023-10-07","cited_by_count":1,"area":null},{"id":"2506.02010","title":"CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2306.08314","title":"Automated Speaker Independent Visual Speech Recognition: A Comprehensive Survey","created":"2023-06-14","cited_by_count":0,"area":null},{"id":"2503.03286","title":"Enhancing Visual Forced Alignment with Local Context-Aware Feature Extraction and Multi-Task Learning","created":"2025-03-05","cited_by_count":0,"area":null},{"id":"2506.16073","title":"TD3Net: A temporal densely connected multi-dilated convolutional network for lipreading","created":"2025-06-19","cited_by_count":0,"area":null},{"id":"2508.02460","title":"InfoSyncNet: Information Synchronization Temporal Convolutional Network for Visual Speech Recognition","created":"2025-08-04","cited_by_count":0,"area":null},{"id":"2508.07233","title":"Landmark Guided Visual Feature Extractor for Visual Speech Recognition with Limited Resource","created":"2025-08-10","cited_by_count":0,"area":null},{"id":"2512.20032","title":"VALLR-Pin: Uncertainty-Factorized Visual Speech Recognition for Mandarin with Pinyin Guidance","created":"2025-12-23","cited_by_count":0,"area":null},{"id":"2607.08112","title":"VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness","created":"2026-07-09","cited_by_count":0,"area":null},{"id":"2610.19559","title":"Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}