{"total":31,"rows":[{"id":"2503.11315","title":"MMS-LLaMA: Efficient LLM-based Audio-Visual Speech Recognition with Minimal Multimodal Speech Tokens","created":"2025-03-14","cited_by_count":19,"area":null},{"id":"2503.06273","title":"Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations","created":"2025-03-08","cited_by_count":9,"area":null},{"id":"2506.02178","title":"Cocktail-Party Audio-Visual Speech Recognition","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2504.15066","title":"Chinese-LiPS: A Chinese audio-visual speech recognition dataset with Lip-reading and Presentation Slides","created":"2025-04-21","cited_by_count":5,"area":null},{"id":"2511.11124","title":"AV-Dialog: Spoken Dialogue Models with Audio-Visual Input","created":"2025-11-14","cited_by_count":5,"area":null},{"id":"2502.01547","title":"mWhisper-Flamingo for Multilingual Audio-Visual Noise-Robust Speech Recognition","created":"2025-02-03","cited_by_count":4,"area":null},{"id":"2511.07253","title":"Omni-AVSR: Towards Unified Multimodal Speech Recognition with Large Language Models","created":"2025-11-10","cited_by_count":4,"area":null},{"id":"2509.12204","title":"Character-Centric Understanding of Animated Movies","created":"2025-09-15","cited_by_count":3,"area":null},{"id":"2603.21664","title":"HumanOmni-Speaker: Identifying Who said What and When","created":"2026-03-23","cited_by_count":3,"area":null},{"id":"2501.04038","title":"Listening and Seeing Again: Generative Error Correction for Audio-Visual Speech Recognition","created":"2025-01-03","cited_by_count":2,"area":null},{"id":"2502.01709","title":"Adapter-Based Multi-Agent AVSR Extension for Pre-Trained ASR Models","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2509.23833","title":"AISHELL6-whisper: A Chinese Mandarin Audio-visual Whisper Speech Dataset with Speech Recognition Baselines","created":"2025-09-28","cited_by_count":2,"area":null},{"id":"2601.18396","title":"Noise-Robust AV-ASR Using Visual Features Both in the Whisper Encoder and Decoder","created":"2026-01-26","cited_by_count":2,"area":null},{"id":"2602.22039","title":"TG-ASR: Translation-Guided Learning with Parallel Gated Cross Attention for Low-Resource Automatic Speech Recognition","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2609.22452","title":"Vox-Infinity: Benchmarking the Limits of Long-Context Spoken Language Models","created":"2026-09-18","cited_by_count":2,"area":null},{"id":"2505.03186","title":"CoGenAV: Versatile Audio-Visual Representation Learning via Contrastive-Generative Synchronization","created":"2025-05-06","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":"2508.07608","title":"AD-AVSR: Asymmetric Dual-stream Enhancement for Robust Audio-Visual Speech Recognition","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2508.18734","title":"Improving Noise Robust Audio-Visual Speech Recognition via Router-Gated Cross-Modal Feature Fusion","created":"2025-08-26","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":"2603.12046","title":"Dr. SHAP-AV: Decoding Relative Modality Contributions via Shapley Attribution in Audio-Visual Speech Recognition","created":"2026-03-12","cited_by_count":1,"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":"2509.16375","title":"Whisper-UT: A Unified Translation Framework for Speech and Text","created":"2025-09-19","cited_by_count":0,"area":null},{"id":"2605.30472","title":"Your Multimodal Speech Model Says I Have a Face for Radio","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.29632","title":"VIB-AVSR: Variational Information Bottleneck for Noise-Robust LLM-Based Audio-Visual Speech Recognition","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.07294","title":"Multimodal Voice Activity Projection for Turn-Taking in Social Robots with Voice-Activity-Related Pretrained Encoders","created":"2026-07-08","cited_by_count":0,"area":null},{"id":"2607.29112","title":"DoubleHelix: Structured Cross-Modal Fusion for Audio-Visual Speech Recognition with LLMs","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.08510","title":"From Speech to Interaction: Analyzing Multimodal Systems in Cocktail-Party Scenarios","created":"2026-08-09","cited_by_count":0,"area":null},{"id":"2608.26213","title":"Attention-Guided Reliability Scaling for Contrastive Decoding in Robust Audio-Visual Speech Recognition","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2608.29239","title":"Anchoring Speech with Semantics: A Multimodal Adapter Mechanism for Automatic Speech Recognition in Low-Resource Languages","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.10394","title":"Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}