{"total":15,"rows":[{"id":"2503.21408","title":"VALLR: Visual ASR Language Model for Lip Reading","created":"2025-03-27","cited_by_count":11,"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":"2108.13630","title":"SimulLR: Simultaneous Lip Reading Transducer with Attention-Guided Adaptive Memory","created":"2021-08-31","cited_by_count":7,"area":null},{"id":"2205.14295","title":"Is Lip Region-of-Interest Sufficient for Lipreading?","created":"2022-05-28","cited_by_count":5,"area":null},{"id":"2303.01758","title":"SottoVoce: An Ultrasound Imaging-Based Silent Speech Interaction Using Deep Neural Networks","created":"2023-03-03","cited_by_count":5,"area":null},{"id":"2104.14467","title":"Towards a practical lip-to-speech conversion system using deep neural networks and mobile application frontend","created":"2021-04-29","cited_by_count":2,"area":null},{"id":"2308.06944","title":"One-shot lip-based biometric authentication: extending behavioral features with authentication phrase information","created":"2023-08-14","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":"2504.15792","title":"Development and evaluation of a deep learning algorithm for German word recognition from lip movements","created":"2025-04-22","cited_by_count":1,"area":null},{"id":"2107.00692","title":"Interactive decoding of words from visual speech recognition models","created":"2021-07-01","cited_by_count":0,"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":"2406.01321","title":"Sequence-to-Sequence Multi-Modal Speech In-Painting","created":"2024-06-03","cited_by_count":0,"area":null},{"id":"2606.00751","title":"Head-Pose-Aware Visual Speech Recognition with FiLM Modulation","created":"2026-05-30","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}