Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Audio Spectrogram Transformer

Audio Spectrogram Transformer

Reported on 6 benchmarks across 4 tasks · 1 paper · 6 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio3 results

Audio ClassificationonESC-50
Accuracy (5-fold)· uses extra data· 2021-04-05
95.7
best: 99.1 (OmniVec2)
SOTA
AST: Audio Spectrogram Transformer arXiv:2104.01778
Audio ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2021-04-05
95.7
best: 99.1 (OmniVec2)
SOTA
AST: Audio Spectrogram Transformer arXiv:2104.01778
Audio TaggingonAudioSet
mean average precision· uses extra data· 2021-04-05
0.485
best: 0.512 (CAV-MAE (Audio-Visual))
SOTA
AST: Audio Spectrogram Transformer arXiv:2104.01778

Methodology2 results

ClassificationonESC-50
Accuracy (5-fold)· uses extra data· 2021-04-05
95.7
best: 99.1 (OmniVec2)
SOTA
AST: Audio Spectrogram Transformer arXiv:2104.01778
ClassificationonESC-50
Top-1 Accuracy· uses extra data· 2021-04-05
95.7
best: 99.1 (OmniVec2)
SOTA
AST: Audio Spectrogram Transformer arXiv:2104.01778

Speech1 result

Keyword SpottingonGoogle Speech Commands
Google Speech Commands V2 35· 2021-04-05
98.11
best: 99.1 (WaveFormer)
SOTA
AST: Audio Spectrogram Transformer arXiv:2104.01778