Audio Classification on AudioSet

Metric: d-prime (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Hide extra data

Sort:

#	Model↕	d-prime▼	Extra Data	Paper	Date↕	Code
1	PSLA (Ensemble)	2.936	Yes	PSLA: Improving Audio Tagging with Pretraining, ...	2021-02-02	Code
2	VATT-Base	2.895	Yes	VATT: Transformers for Multimodal Self-Supervise...	2021-04-22	Code
3	ERANN-1-6	2.804	No	-	-	-
4	PSLA (Single)	2.778	Yes	PSLA: Improving Audio Tagging with Pretraining, ...	2021-02-02	Code
5	PANNs-CNN14 (Single)	2.732	No	-	-	Code

#1PSLA (Ensemble)SOTA
2.936
d-prime· Extra Data· 2021-02-02
PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation Code
#2VATT-Base
2.895
d-prime· Extra Data· 2021-04-22
VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text Code
#3ERANN-1-6
2.804
d-prime
No paper
#4PSLA (Single)
2.778
d-prime· Extra Data· 2021-02-02
PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation Code
#5PANNs-CNN14 (Single)
2.732
d-prime
No paperCode