OpenCodePapers

audio-tagging-on-audioset

Audio Tagging
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
PaperCodemean average precisionModelNameReleaseDate
Contrastive Audio-Visual Masked Autoencoder✓ Link0.512CAV-MAE (Audio-Visual)2022-10-02
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation✓ Link0.498mn40_as (Ensemble)2022-11-09
Efficient Training of Audio Transformers with Patchout✓ Link0.496PaSST2021-10-11
Dynamic Convolutional Neural Networks as Efficient Pre-trained Audio Models✓ Link0.490DyMN-L (Audio-Only, Single)2023-10-24
AST: Audio Spectrogram Transformer✓ Link0.485Audio Spectrogram Transformer2021-04-05
Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation✓ Link0.483mn40_as (Single)2022-11-09
PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation✓ Link0.474PSLA2021-02-02
Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data✓ Link0.467ST-SED2021-12-15
Contrastive Audio-Visual Masked Autoencoder✓ Link0.466CAV-MAE (Audio-Only)2022-10-02
ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition0.450ERANN-1-62021-06-03
PANNs: Large-Scale Pretrained Audio Neural Networks for Audio Pattern Recognition✓ Link0.431CNN142020-08-23