AudioSet

Dataset Card for AudioSet Dataset Summary AudioSet is a dataset of 10-second clips from YouTube, annotated into one or more sound categories, following the AudioSet ontology. Supported Tasks and Leaderboards audio-classification: Classify audio clips into categories. The leaderboard is available here Languages The clas

Papers using AudioSet (5)

GMS-CAVP: Improving Audio-Video Correspondence with Multi-Scale Contrastive and Generative Pretraining2026Self-Supervised MultiModal Versatile Networks2020 · 195 citesBLAT: Bootstrapping Language-Audio Pre-training based on AudioSet Tag-guided Synthetic Data2023Multimodal Transformer With a Low-Computational-Cost Guarantee2024MINT: a Multi-modal Image and Narrative Text Dubbing Dataset for Foley Audio Content Planning and Generation2024