Papers › AST: Audio Spectrogram Transformer

AST: Audio Spectrogram Transformer

5 Apr 2021arXiv:2104.01778archive 2025-07-28

Yuan Gong, Yu-An Chung, James Glass

In the past decade, convolutional neural networks (CNNs) have been widely adopted as the main building block for end-to-end audio classification models, which aim to learn a direct mapping from audio spectrograms to corresponding labels. To better capture long-range global context, a recent trend is to add a self-attention mechanism on top of the CNN, forming a CNN-attention hybrid model. However, it is unclear whether the reliance on a CNN is necessary, and if neural networks purely based on attention are sufficient to obtain good performance in audio classification. In this paper, we answer the question by introducing the Audio Spectrogram Transformer (AST), the first convolution-free, purely attention-based model for audio classification. We evaluate AST on various audio classification benchmarks, where it achieves new state-of-the-art results of 0.485 mAP on AudioSet, 95.6% accuracy on ESC-50, and 98.1% accuracy on Speech Commands V2.

PaperPDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2104.01778")

Code

Syntology Ran 0 of 3 code samples harvested from 1 repository linked to this paper; 3 have no recorded run.

By repository: community (archive-listed): 3 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

YuanGongND/ast officialmentioned in papermentioned on GitHubpytorchBSD-3-Clause report
cgaroufis/msspt mentioned on GitHubtf report
nttcslab/composing-general-audio-repr mentioned on GitHubpytorchNOASSERTION report
pxaris/ccml mentioned on GitHubpytorchApache-2.0 report
pwc-1/Paper-8 mindspore 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

3 samples harvested; 0 ran; 0 honoured the contract we drafted; 3 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

3unverified

Licence: 0 of the 3 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from pxaris/ccml. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

get_warmup_lr pxaris/ccml/training/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 3eb071f1be404988 · report
opt_schedule pxaris/ccml/training/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 7116dd6a41d2b73f · report
train_one_epoch pxaris/ccml/training/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 538dda2cb39fe247 · report

Tasks

Audio ClassificationAudio TaggingClassificationGeneral ClassificationKeyword SpottingSpeech Emotion RecognitionTime Series Analysis

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio Classification AudioSet AST (Ensemble) Test mAP 0.485 #20 of 51 Archive leaderboard report
Audio Classification AudioSet AST (Single) Test mAP 0.459 #37 of 51 Archive leaderboard report
Audio Classification ESC-50 Audio Spectrogram Transformer Accuracy (5-fold) 95.7 #16 of 29 Archive leaderboard report
Audio Classification ESC-50 Audio Spectrogram Transformer PRE-TRAINING DATASET AudioSet, ImageNet #16 of 29 Archive leaderboard report
Audio Classification ESC-50 Audio Spectrogram Transformer Top-1 Accuracy 95.7 #16 of 29 Archive leaderboard report
Audio Classification Speech Commands AST-S Accuracy 98.11±0.05 #2 of 7 Archive leaderboard report
Audio Tagging AudioSet Audio Spectrogram Transformer mean average precision 0.485 #5 of 11 Archive leaderboard report
Keyword Spotting Google Speech Commands Audio Spectrogram Transformer Google Speech Commands V2 35 98.11 #32 of 42 Archive leaderboard report
Speech Emotion Recognition CREMA-D ViT Accuracy 67.81 #7 of 9 Archive leaderboard report
Time Series Analysis Speech Commands ViT % Test Accuracy 98.11 #2 of 6 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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