{"total":62,"rows":[{"id":"2207.06405","title":"Masked Autoencoders that Listen","created":"2022-07-13","cited_by_count":273,"area":null},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267,"area":null},{"id":"2402.01831","title":"Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities","created":"2024-02-02","cited_by_count":186,"area":null},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176,"area":null},{"id":"2407.01494","title":"FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds","created":"2024-07-01","cited_by_count":110,"area":null},{"id":"2309.14405","title":"Joint Audio and Speech Understanding","created":"2023-09-25","cited_by_count":100,"area":null},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59,"area":null},{"id":"2410.18325","title":"AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models","created":"2024-10-23","cited_by_count":56,"area":null},{"id":"2311.15830","title":"A-JEPA: Joint-Embedding Predictive Architecture Can Listen","created":"2023-11-27","cited_by_count":53,"area":null},{"id":"2302.00646","title":"Epic-Sounds: A Large-scale Dataset of Actions That Sound","created":"2023-02-01","cited_by_count":47,"area":null},{"id":"2112.07891","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","created":"2021-12-15","cited_by_count":27,"area":null},{"id":"2503.10522","title":"AudioX: A Unified Framework for Anything-to-Audio Generation","created":"2025-03-13","cited_by_count":27,"area":null},{"id":"2507.08557","title":"FreeAudio: Training-Free Timing Planning for Controllable Long-Form Text-to-Audio Generation","created":"2025-07-11","cited_by_count":21,"area":null},{"id":"2508.06098","title":"MeanAudio: Fast and Faithful Text-to-Audio Generation with Mean Flows","created":"2025-08-08","cited_by_count":14,"area":null},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2604.10708","title":"Audio-Omni: Extending Multi-modal Understanding to Versatile Audio Generation and Editing","created":"2026-04-12","cited_by_count":12,"area":null},{"id":"2109.00962","title":"You Only Hear Once: A YOLO-like Algorithm for Audio Segmentation and Sound Event Detection","created":"2021-09-01","cited_by_count":10,"area":null},{"id":"2307.06860","title":"AnuraSet: A dataset for benchmarking Neotropical anuran calls identification in passive acoustic monitoring","created":"2023-07-11","cited_by_count":10,"area":null},{"id":"2409.10999","title":"Enhancing Low-Resource Language and Instruction Following Capabilities of Audio Language Models","created":"2024-09-17","cited_by_count":10,"area":null},{"id":"2305.09690","title":"A Whisper transformer for audio captioning trained with synthetic captions and transfer learning","created":"2023-05-15","cited_by_count":9,"area":null},{"id":"2505.07609","title":"TACOS: Temporally-aligned Audio CaptiOnS for Language-Audio Pretraining","created":"2025-05-12","cited_by_count":9,"area":null},{"id":"2507.16343","title":"Detect Any Sound: Open-Vocabulary Sound Event Detection with Multi-Modal Queries","created":"2025-07-22","cited_by_count":9,"area":null},{"id":"2203.15135","title":"Filler Word Detection and Classification: A Dataset and Benchmark","created":"2022-03-28","cited_by_count":7,"area":null},{"id":"2404.07616","title":"Audio Dialogues: Dialogues dataset for audio and music understanding","created":"2024-04-11","cited_by_count":7,"area":null},{"id":"2308.04258","title":"Advancing Natural-Language Based Audio Retrieval with PaSST and Large Audio-Caption Data Sets","created":"2023-08-08","cited_by_count":6,"area":null},{"id":"2409.06223","title":"Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models","created":"2024-09-10","cited_by_count":5,"area":null},{"id":"2507.09834","title":"Generative Audio Language Modeling with Continuous-valued Tokens and Masked Next-Token Prediction","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2603.09677","title":"Logics-Parsing-Omni Technical Report","created":"2026-03-10","cited_by_count":5,"area":null},{"id":"2109.14061","title":"The impact of non-target events in synthetic soundscapes for sound event detection","created":"2021-09-28","cited_by_count":4,"area":null},{"id":"2202.02441","title":"SEED: Sound Event Early Detection via Evidential Uncertainty","created":"2022-02-05","cited_by_count":4,"area":null},{"id":"2403.08525","title":"From Weak to Strong Sound Event Labels using Adaptive Change-Point Detection and Active Learning","created":"2024-03-13","cited_by_count":4,"area":null},{"id":"2410.16505","title":"Do Audio-Language Models Understand Linguistic Variations?","created":"2024-10-21","cited_by_count":4,"area":null},{"id":"2509.18606","title":"FlexSED: Towards Open-Vocabulary Sound Event Detection","created":"2025-09-23","cited_by_count":4,"area":null},{"id":"2510.22795","title":"SAO-Instruct: Free-form Audio Editing using Natural Language Instructions","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2409.17656","title":"Prototype based Masked Audio Model for Self-Supervised Learning of Sound Event Detection","created":"2024-09-26","cited_by_count":3,"area":null},{"id":"2412.18157","title":"Smooth-Foley: Creating Continuous Sound for Video-to-Audio Generation Under Semantic Guidance","created":"2024-12-24","cited_by_count":3,"area":null},{"id":"2511.15131","title":"CASTELLA: Long Audio Dataset with Captions and Temporal Boundaries","created":"2025-11-19","cited_by_count":3,"area":null},{"id":"2506.23437","title":"From Large-scale Audio Tagging to Real-Time Explainable Emergency Vehicle Sirens Detection","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2508.20976","title":"WoW-Bench: Evaluating Fine-Grained Acoustic Perception in Audio-Language Models via Marine Mammal Vocalizations","created":"2025-08-28","cited_by_count":2,"area":null},{"id":"2509.05256","title":"Recomposer: Event-roll-guided generative audio editing","created":"2025-09-05","cited_by_count":2,"area":null},{"id":"2202.01487","title":"A benchmark of state-of-the-art sound event detection systems evaluated on synthetic soundscapes","created":"2022-02-03","cited_by_count":1,"area":null},{"id":"2309.13086","title":"Towards Lexical Analysis of Dog Vocalizations via Online Videos","created":"2023-09-21","cited_by_count":1,"area":null},{"id":"2410.12028","title":"EmotionCaps: Enhancing Audio Captioning Through Emotion-Augmented Data Generation","created":"2024-10-15","cited_by_count":1,"area":null},{"id":"2411.15447","title":"Gotta Hear Them All: Towards Sound Source Aware Audio Generation","created":"2024-11-23","cited_by_count":1,"area":null},{"id":"2502.09363","title":"The Accuracy Cost of Weakness: A Theoretical Analysis of Fixed-Segment Weak Labeling for Events in Time","created":"2025-02-13","cited_by_count":1,"area":null},{"id":"2603.25767","title":"Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2606.15186","title":"FreeSonic: Training-Free Temporal-Aware Decoupled Attention for Precise Audio Editing","created":"2026-06-13","cited_by_count":1,"area":null},{"id":"2607.16736","title":"RealDESED: A Real-World Domestic Sound Event Detection Benchmark","created":"2026-07-18","cited_by_count":1,"area":null},{"id":"2608.29999","title":"TEMPO: Temporally-grounded Multi-task Post-training for Large Audio-Language Models","created":"2026-08-30","cited_by_count":1,"area":null},{"id":"2405.11093","title":"AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations","created":"2024-05-17","cited_by_count":0,"area":null},{"id":"2409.09381","title":"Text Prompt is Not Enough: Sound Event Enhanced Prompt Adapter for Target Style Audio Generation","created":"2024-09-14","cited_by_count":0,"area":null},{"id":"2503.11373","title":"Exploring Performance-Complexity Trade-Offs in Sound Event Detection Models","created":"2025-03-14","cited_by_count":0,"area":null},{"id":"2503.15338","title":"Solla: Towards a Speech-Oriented LLM That Hears Acoustic Context","created":"2025-03-19","cited_by_count":0,"area":null},{"id":"2504.04428","title":"Formula-Supervised Sound Event Detection: Pre-Training Without Real Data","created":"2025-04-06","cited_by_count":0,"area":null},{"id":"2507.01563","title":"Real-Time Emergency Vehicle Siren Detection with Efficient CNNs on Embedded Hardware","created":"2025-07-02","cited_by_count":0,"area":null},{"id":"2603.27667","title":"EvA: An Evidence-First Audio Understanding Paradigm for LALMs","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2606.09331","title":"Conan-embedding-v3: Fusing Modality-Specific Models for Omni-Modal Embedding","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.13571","title":"Cover First, Disagree Softly: Rethinking Mismatch-First Active Learning for Frame-Level Audio Classification","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2609.02343","title":"SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.15562","title":"PIVOT: Physics-Grounded Verification for AI-Generated Audio-Video Detection","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.34030","title":"Uncovering shortcut learning in audio classifiers by discovering recurring concepts in temporal explanations","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}