Papers › PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation

PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation

2 Feb 2021arXiv:2102.01243archive 2025-07-28

Yuan Gong, Yu-An Chung, James Glass

Audio tagging is an active research area and has a wide range of applications. Since the release of AudioSet, great progress has been made in advancing model performance, which mostly comes from the development of novel model architectures and attention modules. However, we find that appropriate training techniques are equally important for building audio tagging models with AudioSet, but have not received the attention they deserve. To fill the gap, in this work, we present PSLA, a collection of training techniques that can noticeably boost the model accuracy including ImageNet pretraining, balanced sampling, data augmentation, label enhancement, model aggregation and their design choices. By training an EfficientNet with these techniques, we obtain a single model (with 13.6M parameters) and an ensemble model that achieve mean average precision (mAP) scores of 0.444 and 0.474 on AudioSet, respectively, outperforming the previous best system of 0.439 with 81M parameters. In addition, our model also achieves a new state-of-the-art mAP of 0.567 on FSD50K.

Paper PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

YuanGongND/psla officialmentioned in papermentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Audio Classification Audio Tagging Data Augmentation General Classification

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
Audio Classification	AudioSet	PSLA (Ensemble)	AUC	0.981	#30 of 51	Archive leaderboard	report
Audio Classification	AudioSet	PSLA (Ensemble)	Test mAP	0.474	#30 of 51	Archive leaderboard	report
Audio Classification	AudioSet	PSLA (Ensemble)	d-prime	2.936	#30 of 51	Archive leaderboard	report
Audio Classification	AudioSet	PSLA (Single)	AUC	0.975	#40 of 51	Archive leaderboard	report
Audio Classification	AudioSet	PSLA (Single)	Test mAP	0.443	#40 of 51	Archive leaderboard	report
Audio Classification	AudioSet	PSLA (Single)	d-prime	2.778	#40 of 51	Archive leaderboard	report
Audio Classification	FSD50K	PSLA	mAP	56.71	#6 of 10	Archive leaderboard	report
Audio Tagging	AudioSet	PSLA	mean average precision	0.474	#7 of 11	Archive leaderboard	report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 Convolution Average Pooling Batch Normalization Convolution Dense Connections Depthwise Convolution Depthwise Separable Convolution Dropout EfficientNet Inverted Residual Block Pointwise Convolution RMSProp ReLU Sigmoid Activation Squeeze-and-Excitation Block

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections