{"total":21,"rows":[{"id":"2208.12415","title":"MuLan: A Joint Embedding of Music Audio and Natural Language","created":"2022-08-26","cited_by_count":87,"area":null},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"id":"2212.03814","title":"iQuery: Instruments as Queries for Audio-Visual Sound Separation","created":"2022-12-07","cited_by_count":29,"area":null},{"id":"2207.10141","title":"AudioScopeV2: Audio-Visual Attention Architectures for Calibrated Open-Domain On-Screen Sound Separation","created":"2022-07-20","cited_by_count":24,"area":null},{"id":"2212.07065","title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","created":"2022-12-14","cited_by_count":23,"area":null},{"id":"2211.02250","title":"Real-Time Target Sound Extraction","created":"2022-11-04","cited_by_count":22,"area":null},{"id":"2303.16342","title":"Language-Guided Audio-Visual Source Separation via Trimodal Consistency","created":"2023-03-28","cited_by_count":20,"area":null},{"id":"2311.00320","title":"Semantic Hearing: Programming Acoustic Scenes with Binaural Hearables","created":"2023-11-01","cited_by_count":11,"area":null},{"id":"2310.07284","title":"Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction","created":"2023-10-11","cited_by_count":6,"area":null},{"id":"2402.03710","title":"Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience","created":"2024-02-06","cited_by_count":6,"area":null},{"id":"2211.05927","title":"Optimal Condition Training for Target Source Separation","created":"2022-11-11","cited_by_count":5,"area":null},{"id":"2404.01740","title":"Weakly-supervised Audio Separation via Bi-modal Semantic Similarity","created":"2024-04-02","cited_by_count":5,"area":null},{"id":"2301.03238","title":"MAQA: A Multimodal QA Benchmark for Negation","created":"2023-01-09","cited_by_count":4,"area":null},{"id":"2409.19270","title":"OpenSep: Leveraging Large Language Models with Textual Inversion for Open World Audio Separation","created":"2024-09-28","cited_by_count":2,"area":null},{"id":"2506.00273","title":"SoundSculpt: Direction and Semantics Driven Ambisonic Target Sound Extraction","created":"2025-05-30","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":"2307.14609","title":"Complete and separate: Conditional separation with missing target source attribute completion","created":"2023-07-27","cited_by_count":0,"area":null},{"id":"2403.14246","title":"CATSE: A Context-Aware Framework for Causal Target Sound Extraction","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2505.21025","title":"Text-Queried Audio Source Separation via Hierarchical Modeling","created":"2025-05-27","cited_by_count":0,"area":null},{"id":"2603.00395","title":"Fine-grained Soundscape Control for Augmented Hearing","created":"2026-02-28","cited_by_count":0,"area":null},{"id":"2609.36577","title":"Long-Term Memory-Guided Enhancement for Target Perception in Audio-Language Models","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}