{"total":17,"rows":[{"id":"2401.05698","title":"HiCMAE: Hierarchical Contrastive Masked Autoencoder for Self-Supervised Audio-Visual Emotion Recognition","created":"2024-01-11","cited_by_count":30,"area":null},{"id":"2406.10083","title":"On the Evaluation of Speech Foundation Models for Spoken Language Understanding","created":"2024-06-14","cited_by_count":9,"area":null},{"id":"2601.12248","title":"AQUA-Bench: Beyond Finding Answers to Knowing When There Are None in Audio Question Answering","created":"2026-01-18","cited_by_count":6,"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":"2505.06660","title":"TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models","created":"2025-05-10","cited_by_count":4,"area":null},{"id":"2509.07139","title":"The ML-SUPERB 2.0 Challenge: Towards Inclusive ASR Benchmarking for All Language Varieties","created":"2025-09-08","cited_by_count":4,"area":null},{"id":"2604.25591","title":"Walking Through Uncertainty: An Empirical Study of Uncertainty Estimation for Audio-Aware Large Language Models","created":"2026-04-28","cited_by_count":4,"area":null},{"id":"2404.18327","title":"MultiMAE-DER: Multimodal Masked Autoencoder for Dynamic Emotion Recognition","created":"2024-04-28","cited_by_count":3,"area":null},{"id":"2409.12306","title":"Measuring Sound Symbolism in Audio-visual Models","created":"2024-09-18","cited_by_count":3,"area":null},{"id":"2606.07435","title":"The Lipreading Gap: Do VSR Models Perceive Visual Speech Like Human Lipreaders?","created":"2026-06-05","cited_by_count":3,"area":null},{"id":"2512.06380","title":"Protecting Bystander Privacy via Selective Hearing in Audio LLMs","created":"2025-12-06","cited_by_count":2,"area":null},{"id":"2507.07883","title":"SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation","created":"2025-07-10","cited_by_count":1,"area":null},{"id":"2601.06329","title":"On the Fallacy of Global Token Perplexity in Spoken Language Model Evaluation","created":"2026-01-09","cited_by_count":1,"area":null},{"id":"2402.13004","title":"Comparison of Conventional Hybrid and CTC/Attention Decoders for Continuous Visual Speech Recognition","created":"2024-02-20","cited_by_count":0,"area":null},{"id":"2412.14965","title":"Movie2Story: A framework for understanding videos and telling stories in the form of novel text","created":"2024-12-19","cited_by_count":0,"area":null},{"id":"2506.01275","title":"Contra4: Evaluating Contrastive Cross-Modal Reasoning in Audio, Video, Image, and 3D","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2512.11901","title":"CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities","created":"2025-12-10","cited_by_count":0,"area":null}],"next_cursor":null}