Researchers have developed Auto-AEG, a scalable pipeline designed to construct supervision data for open-vocabulary audio event grounding. This task aims to precisely locate sound events described by natural language queries within audio, a capability that current large audio-language models (LALMs) lack. Auto-AEG addresses data scarcity by combining synthesized audio clips with exact temporal annotations and pseudo-labels from real-world audio, enabling fine-tuning for improved performance on benchmarks like DESED SED and AEGBench. AI
IMPACT Enhances the temporal localization capabilities of large audio-language models, enabling more precise real-world audio understanding.
RANK_REASON The cluster contains an academic paper detailing a new method for audio event grounding. [lever_c_demoted from research: ic=1 ai=1.0]
- AEGBench
- arXiv
- Auto-AEG
- DESED SED benchmark
- Large Audio-Language Models
- Open-Vocabulary Audio Event Grounding
- Sound Event Detection by Pseudo-Labeling in Weakly Labeled Dataset
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
