AudioSet

Overview edit

Variants: AudioSet

Associated Benchmarks

This dataset is used in 5 benchmarks:

• Audio Classification - Metrics: Test mAP, AUC, d-prime
• Audio Tagging - Metrics: mean average precision
• Audio Source Separation - Metrics: SDR, SAR, SIR
• Target Sound Extraction - Metrics: SDRi, SI-SDRi
• Multi-modal Classification - Metrics: Average mAP

Recent Benchmark Submissions

Research Papers

Recent papers with results on this dataset:

• SSLAM: Enhancing Self-Supervised Models with Audio Mixtures for Polyphonic Soundscapes (2025) -
• M2D2: Exploring General-purpose Audio-Language Representations Beyond CLAP (2025) -
• DASS: Distilled Audio State Space Models Are Stronger and More Duration-Scalable Learners (2024) -
• M2D-CLAP: Masked Modeling Duo Meets CLAP for Learning General-purpose Audio-Language Representation (2024) -
• Masked Modeling Duo: Towards a Universal Audio Pre-training Framework (2024) -
• EquiAV: Leveraging Equivariance for Audio-Visual Contrastive Learning (2024) -
• CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction (2024) -
• EAT: Self-Supervised Pre-Training with Efficient Audio Transformer (2024) -
• OmniVec: Learning robust representations with cross modal sharing (2023) -
• Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models (2023) -
• Self-supervised Audio Teacher-Student Transformer for Both Clip-level and Frame-level Tasks (2023) -
• BEATs: Audio Pre-Training with Acoustic Tokenizers (2022) -
• Audiovisual Masked Autoencoders (2022) -
• Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation (2022) -
• Play It Back: Iterative Attention for Audio Recognition (2022) -
• Contrastive Audio-Visual Masked Autoencoder (2022) -
• UAVM: Towards Unifying Audio and Visual Models (2022) -
• End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network (2022) -
• HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection (2022) -
• Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data (2021) -