CoChat

AST: Audio Spectrogram Transformer

Gong, Yuan, Chung, Yu-An, Glass, James · 2021 · Interspeech 2021

The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.

Abstract

In the past decade, convolutional neural networks (CNNs) have been widely adopted as the main building block for endto-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.

Overview

Integrity signals

Registry

Crossref · 10.21437/interspeech.2021-698

Cites

35 of 35 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Cited by

See all 1,159

Metadata

Authors
Gong, Y., Chung, Y.-A., & Glass, J.
Affiliations
MIT Computer Science and Artificial Intelligence Laboratory (US)
Venue
Interspeech 2021
Publisher
ISCA
Published
2021-08-30
Pages
571-575
ISSN
2308-457X (ISSN-L)
OpenAlex
W3196974791
Cited by
1,159
References
33
Citations by year
2026: 260 · 2025: 356 · 2024: 241 · 2023: 193 · 2022: 100 · 2021: 9
FWCI
82.22
Type
conference paper
Language
en
Open access
closed
Locations
Interspeech (USB) (publishedVersion)
Topics
  • Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
  • Physical Sciences › Computer Science › Artificial Intelligence › Speech Recognition and Synthesis
  • Physical Sciences › Computer Science › Signal Processing › Speech and Audio Processing
Keywords
Audio Spectrogram Transformer, audio classification, self-attention, spectrogram, AudioSet, ESC-50

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.