{"ID":5937734,"CreatedAt":"2026-07-07T03:14:33.014478982Z","UpdatedAt":"2026-07-08T16:08:56.472507517Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.04383","arxiv_id":"2607.04383","title":"Auto-AEG: Scalable Data Construction for Open-Vocabulary Audio Event Grounding","abstract":"Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set. At the intersection of these paradigms lies the task of Open-Vocabulary Audio Event Grounding: predicting all time intervals of a target sound event described by an arbitrary natural language query. While this task is crucial for real-world audio understanding and LALM adaptation, it is bottlenecked by data scarcity. Few large-scale resources provide open-vocabulary onset/offset supervision, and manual temporal annotation is prohibitively expensive. To address this, we introduce Auto-AEG, a scalable pipeline that constructs such supervision by automatic data construction and model fine-tuning. It pairs programmatically synthesized clips, which carry exact ground-truth intervals for supervised cold-start, with multi-model pseudo-labels on real-world audio that supply the reward signal for reinforcement learning. Training with this pipeline yields promising performance gains on both the DESED SED benchmark and AEGBench, an independent difficulty-stratified benchmark we release. Our results show that automatically constructed data, coupled with interval-aware reward function design, is an effective data-side route to expanding the temporal localization capability of LALMs.","short_abstract":"Large Audio-Language Models (LALMs) reason fluently about sound yet struggle to localize precisely when events occur, while classical Sound Event Detection attains frame-level precision only over a closed label set. At the intersection of these paradigms lies the task of Open-Vocabulary Audio Event Grounding: predictin...","url_abs":"https://arxiv.org/abs/2607.04383","url_pdf":"https://arxiv.org/pdf/2607.04383v1","authors":"[\"Zihan Zhang\",\"Xize Cheng\",\"Wenhao Yan\",\"Tong Zhang\",\"Dongjie Fu\",\"Boyun Zhang\",\"Yongbo He\",\"Tao Jin\"]","published":"2026-07-05T16:22:14Z","proceeding":"cs.SD","tasks":"[\"cs.SD\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Language Model\"]","has_code":false}