Papers › End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio...

End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network

25 Apr 2022arXiv:2204.11479archive 2025-07-28

Avi Gazneli, Gadi Zimerman, Tal Ridnik, Gilad Sharir, Asaf Noy

While efficient architectures and a plethora of augmentations for end-to-end image classification tasks have been suggested and heavily investigated, state-of-the-art techniques for audio classifications still rely on numerous representations of the audio signal together with large architectures, fine-tuned from large datasets. By utilizing the inherited lightweight nature of audio and novel audio augmentations, we were able to present an efficient end-to-end network with strong generalization ability. Experiments on a variety of sound classification sets demonstrate the effectiveness and robustness of our approach, by achieving state-of-the-art results in various settings. Public code is available at: \href{https://github.com/Alibaba-MIIL/AudioClassfication}{this http url}

PaperPDFCode

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

Code

Alibaba-MIIL/AudioClassfication 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 ClassificationClassificationEnvironmental Sound ClassificationKeyword SpottingSound Classificationimage-classification

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio Classification AudioSet EAT-M Test mAP 0.426 #42 of 51 Archive leaderboard report
Audio Classification AudioSet EAT-S Test mAP 0.405 #44 of 51 Archive leaderboard report
Audio Classification ESC-50 EAT-M Accuracy (5-fold) 96.3 #11 of 29 Archive leaderboard report
Audio Classification ESC-50 EAT-M PRE-TRAINING DATASET AudioSet #11 of 29 Archive leaderboard report
Audio Classification ESC-50 EAT-M Top-1 Accuracy 96.3 #11 of 29 Archive leaderboard report
Audio Classification ESC-50 EAT-S Accuracy (5-fold) 95.25 #17 of 29 Archive leaderboard report
Audio Classification ESC-50 EAT-S PRE-TRAINING DATASET AudioSet #17 of 29 Archive leaderboard report
Audio Classification ESC-50 EAT-S Top-1 Accuracy 95.25 #17 of 29 Archive leaderboard report
Audio Classification ESC-50 EAT-S (scratch) Accuracy (5-fold) 92.15 #19 of 29 Archive leaderboard report
Audio Classification ESC-50 EAT-S (scratch) Top-1 Accuracy 92.15 #19 of 29 Archive leaderboard report
Keyword Spotting Google Speech Commands EAT-S Google Speech Commands V2 35 98.15 #31 of 42 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.

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