Papers › EAT: Self-Supervised Pre-Training with Efficient Audio Transformer

EAT: Self-Supervised Pre-Training with Efficient Audio Transformer

7 Jan 2024arXiv:2401.03497archive 2025-07-28

Wenxi Chen, Yuzhe Liang, Ziyang Ma, Zhisheng Zheng, Xie Chen

Audio self-supervised learning (SSL) pre-training, which aims to learn good representations from unlabeled audio, has made remarkable progress. However, the extensive computational demands during pre-training pose a significant barrier to the potential application and optimization of audio SSL models. In this paper, inspired by the success of data2vec 2.0 in image modality and Audio-MAE in audio modality, we introduce Efficient Audio Transformer (EAT) to further improve the effectiveness and efficiency in audio SSL. The proposed EAT adopts the bootstrap self-supervised training paradigm to the audio domain. A novel Utterance-Frame Objective (UFO) is designed to enhance the modeling capability of acoustic events. Furthermore, we reveal that the masking strategy is critical in audio SSL pre-training, and superior audio representations can be obtained with large inverse block masks. Experiment results demonstrate that EAT achieves state-of-the-art (SOTA) performance on a range of audio-related tasks, including AudioSet (AS-2M, AS-20K), ESC-50, and SPC-2, along with a significant pre-training speedup up to ~15x compared to existing audio SSL models.

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="2401.03497")

Code

Syntology Ran 13 of 17 code samples harvested from 1 repository linked to this paper; 4 have no recorded run. Of those that ran: 13 ran with no contract checked.

By repository: official repository: 17 samples from 1 repository, 13 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

cwx-worst-one/eat officialmentioned in papermentioned on GitHubpytorchMIT 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

17 samples harvested; 13 ran; 0 honoured the contract we drafted; 4 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.

13ran
4unverified

Licence: 0 of the 17 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 cwx-worst-one/eat. “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.

build_dictionary cwx-worst-one/eat/inference/inference.py official repository ran MIT (permissive) · 6a3e3a9bf8ae9914 · report
compute_block_mask_1d cwx-worst-one/eat/utils/data_utils.py official repository ran MIT (permissive) · 66f7af815e734d4e · report
compute_block_mask_2d cwx-worst-one/eat/utils/data_utils.py official repository ran MIT (permissive) · 067591e38407a2be · report
compute_mask_indices cwx-worst-one/eat/utils/data_utils.py official repository ran MIT (permissive) · c4e0295ea525f219 · report
extract_feature_tensor cwx-worst-one/eat/feature_extract/feature_extract.py official repository ran MIT (permissive) · 22d21a785404efe9 · report
get_2d_sincos_pos_embed cwx-worst-one/eat/models/mae.py official repository ran fingerprinted MIT (permissive) · 77e8a3ac46f3afec · report
get_2d_sincos_pos_embed_flexible cwx-worst-one/eat/models/mae.py official repository ran MIT (permissive) · 68fc090d0a502993 · report
get_annealed_rate cwx-worst-one/eat/models/base.py official repository ran MIT (permissive) · 5d5be3c7916a67cb · report
get_layer_id_for_vit cwx-worst-one/eat/models/EAT_audio_classification.py official repository ran fingerprinted MIT (permissive) · 3f903f847b8f7f28 · report
mixup_target cwx-worst-one/eat/utils/mixup.py official repository ran MIT (permissive) · 6b945011d5d4e179 · report
one_hot cwx-worst-one/eat/utils/mixup.py official repository ran MIT (permissive) · 6caffa789f1bdabe · report
rand_bbox cwx-worst-one/eat/utils/mixup.py official repository ran MIT (permissive) · 3913c620f6926f42 · report
random_masking cwx-worst-one/eat/models/base.py official repository ran MIT (permissive) · ee9ac852b4eb7975 · report
gather_unmasked cwx-worst-one/eat/models/base.py official repository unverified MIT (permissive) · 3a95f65cb24c84e6 · report
load_model cwx-worst-one/eat/feature_extract/feature_extract.py official repository unverified MIT (permissive) · a663b7a41d863edb · report
load_model cwx-worst-one/eat/inference/inference.py official repository unverified MIT (permissive) · 31694976f9ae8e78 · report
modify_relative_position_bias cwx-worst-one/eat/models/mae.py official repository unverified MIT (permissive) · 915281feeb90ee5a · report

Tasks

Audio ClassificationSelf-Supervised LearningSound Classification

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Audio Classification AudioSet EAT Test mAP 0.486 #18 of 51 Archive leaderboard report
Audio Classification Balanced Audio Set EAT Mean AP 40.3 #3 of 8 Archive leaderboard report
Audio Classification ESC-50 EAT Accuracy (5-fold) 96.0 #15 of 29 Archive leaderboard report
Audio Classification ESC-50 EAT PRE-TRAINING DATASET AudioSet #15 of 29 Archive leaderboard report
Audio Classification ESC-50 EAT Top-1 Accuracy 96.0 #15 of 29 Archive leaderboard report
Audio Classification Speech Commands EAT Accuracy 98.3±0.04 #1 of 7 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