{"total":57,"rows":[{"id":"2201.02184","title":"Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction","created":"2022-01-05","cited_by_count":287,"area":null},{"id":"2102.06657","title":"End-to-end Audio-visual Speech Recognition with Conformers","created":"2021-02-12","cited_by_count":151,"area":null},{"id":"2202.13084","title":"Visual Speech Recognition for Multiple Languages in the Wild","created":"2022-02-26","cited_by_count":95,"area":null},{"id":"2306.10799","title":"SelfTalk: A Self-Supervised Commutative Training Diagram to Comprehend 3D Talking Faces","created":"2023-06-19","cited_by_count":68,"area":null},{"id":"2110.07603","title":"Sub-word Level Lip Reading With Visual Attention","created":"2021-10-14","cited_by_count":63,"area":null},{"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":"2211.11275","title":"VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning","created":"2022-11-21","cited_by_count":37,"area":null},{"id":"2201.10439","title":"Transformer-Based Video Front-Ends for Audio-Visual Speech Recognition for Single and Multi-Person Video","created":"2022-01-25","cited_by_count":31,"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":"2104.13332","title":"End-to-End Video-To-Speech Synthesis using Generative Adversarial Networks","created":"2021-04-27","cited_by_count":27,"area":null},{"id":"2302.06419","title":"AV-data2vec: Self-supervised Learning of Audio-Visual Speech Representations with Contextualized Target Representations","created":"2023-02-10","cited_by_count":27,"area":null},{"id":"2209.14156","title":"TVLT: Textless Vision-Language Transformer","created":"2022-09-28","cited_by_count":22,"area":null},{"id":"2301.01456","title":"Audio-Visual Efficient Conformer for Robust Speech Recognition","created":"2023-01-04","cited_by_count":22,"area":null},{"id":"2205.10839","title":"Deep Learning for Visual Speech Analysis: A Survey","created":"2022-05-22","cited_by_count":21,"area":null},{"id":"2303.17200","title":"SynthVSR: Scaling Up Visual Speech Recognition With Synthetic Supervision","created":"2023-03-30","cited_by_count":21,"area":null},{"id":"2404.02098","title":"BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition","created":"2024-04-02","cited_by_count":21,"area":null},{"id":"2308.07593","title":"AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model","created":"2023-08-15","cited_by_count":16,"area":null},{"id":"2411.02256","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","created":"2024-11-04","cited_by_count":15,"area":null},{"id":"2111.10139","title":"More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech","created":"2021-11-19","cited_by_count":12,"area":null},{"id":"2308.06112","title":"Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping","created":"2023-08-11","cited_by_count":12,"area":null},{"id":"2110.15957","title":"Visual Keyword Spotting with Attention","created":"2021-10-29","cited_by_count":11,"area":null},{"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":"2302.10915","title":"Conformers are All You Need for Visual Speech Recognition","created":"2023-02-17","cited_by_count":9,"area":null},{"id":"2303.09797","title":"MMFace4D: A Large-Scale Multi-Modal 4D Face Dataset for Audio-Driven 3D Face Animation","created":"2023-03-17","cited_by_count":8,"area":null},{"id":"2401.09759","title":"SlideAVSR: A Dataset of Paper Explanation Videos for Audio-Visual Speech Recognition","created":"2024-01-18","cited_by_count":7,"area":null},{"id":"2312.09727","title":"LiteVSR: Efficient Visual Speech Recognition by Learning from Speech Representations of Unlabeled Data","created":"2023-12-15","cited_by_count":6,"area":null},{"id":"2109.09536","title":"Audio-Visual Speech Recognition is Worth 32$\\times$32$\\times$8 Voxels","created":"2021-09-20","cited_by_count":5,"area":null},{"id":"2309.17395","title":"AV-CPL: Continuous Pseudo-Labeling for Audio-Visual Speech Recognition","created":"2023-09-29","cited_by_count":5,"area":null},{"id":"2406.10313","title":"CNVSRC 2023: The First Chinese Continuous Visual Speech Recognition Challenge","created":"2024-06-14","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":"2205.05206","title":"Best of Both Worlds: Multi-task Audio-Visual Automatic Speech Recognition and Active Speaker Detection","created":"2022-05-10","cited_by_count":4,"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":"2410.16438","title":"AlignVSR: Audio-Visual Cross-Modal Alignment for Visual Speech Recognition","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2202.10594","title":"Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Survey","created":"2022-02-22","cited_by_count":3,"area":null},{"id":"2205.05586","title":"End-to-End Multi-Person Audio/Visual Automatic Speech Recognition","created":"2022-05-11","cited_by_count":3,"area":null},{"id":"2205.05684","title":"A Closer Look at Audio-Visual Multi-Person Speech Recognition and Active Speaker Selection","created":"2022-05-11","cited_by_count":3,"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":"2308.08849","title":"A Survey on Deep Multi-modal Learning for Body Language Recognition and Generation","created":"2023-08-17","cited_by_count":3,"area":null},{"id":"2409.09221","title":"Multi-modal Speech Transformer Decoders: When Do Multiple Modalities Improve Accuracy?","created":"2024-09-13","cited_by_count":2,"area":null},{"id":"2204.00652","title":"End-to-end multi-talker audio-visual ASR using an active speaker attention module","created":"2022-04-01","cited_by_count":1,"area":null},{"id":"2305.14203","title":"Improving the Gap in Visual Speech Recognition Between Normal and Silent Speech Based on Metric Learning","created":"2023-05-23","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":"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":"2506.02010","title":"CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.02012","title":"Leveraging Large Language Models in Visual Speech Recognition: Model Scaling, Context-Aware Decoding, and Iterative Polishing","created":"2025-05-27","cited_by_count":1,"area":null},{"id":"2506.04635","title":"ViCocktail: Automated Multi-Modal Data Collection for Vietnamese Audio-Visual Speech Recognition","created":"2025-06-05","cited_by_count":1,"area":null},{"id":"2508.20476","title":"Towards Inclusive Communication: A Unified Framework for Generating Spoken Language from Sign, Lip, and Audio","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2602.19316","title":"Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition","created":"2026-02-22","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":"2110.03354","title":"$\\bar{G}_{mst}$:An Unbiased Stratified Statistic and a Fast Gradient Optimization Algorithm Based on It","created":"2021-10-07","cited_by_count":0,"area":null},{"id":"2202.10923","title":"MSTGD:A Memory Stochastic sTratified Gradient Descent Method with an Exponential Convergence Rate","created":"2022-02-21","cited_by_count":0,"area":null},{"id":"2305.00552","title":"Deep Learning-based Spatio Temporal Facial Feature Visual Speech Recognition","created":"2023-04-30","cited_by_count":0,"area":null},{"id":"2306.13420","title":"Towards Unseen Triples: Effective Text-Image-joint Learning for Scene Graph Generation","created":"2023-06-23","cited_by_count":0,"area":null},{"id":"2409.07210","title":"Enhancing CTC-Based Visual Speech Recognition","created":"2024-09-11","cited_by_count":0,"area":null},{"id":"2410.12435","title":"Approaching Metaheuristic Deep Learning Combos for Automated Data Mining","created":"2024-10-16","cited_by_count":0,"area":null},{"id":"2609.20839","title":"Curriculum-Based Noise Adaptation for Phoneme-to-Text Reconstruction in Visual Speech Recognition","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}