{"total":16,"rows":[{"id":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"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":"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":"2109.06692","title":"LRWR: Large-Scale Benchmark for Lip Reading in Russian language","created":"2021-09-14","cited_by_count":5,"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":"2110.07879","title":"Advances and Challenges in Deep Lip Reading","created":"2021-10-15","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":"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":"2303.10770","title":"RN-Net: Reservoir Nodes-Enabled Neuromorphic Vision Sensing Network","created":"2023-03-19","cited_by_count":3,"area":null},{"id":"2404.11979","title":"MTGA: Multi-View Temporal Granularity Aligned Aggregation for Event-Based Lip-Reading","created":"2024-04-18","cited_by_count":3,"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":"2110.06507","title":"Perception Point: Identifying Critical Learning Periods in Speech for Bilingual Networks","created":"2021-10-13","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}],"next_cursor":null}