Ast: Audio spectrogram transformer

Y Gong, YA Chung, J Glass�- arXiv preprint arXiv:2104.01778, 2021 - arxiv.org
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�…
Save Cite Cited by 799 Related articles View as HTML
[PDF] researchgate.net

[PDF][PDF] AST: Audio Spectrogram Transformer

Y Gong, YA Chung, J Glass - 2021 - researchgate.net
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�…
Cite
[PDF] mit.edu

[PDF][PDF] AST: Audio Spectrogram Transformer

Y Gong, YA Chung, J Glass - 2021 - groups.csail.mit.edu
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�…
Cite

AST: Audio Spectrogram Transformer

Y Gong, YA Chung, J Glass�- arXiv e-prints, 2021 - ui.adsabs.harvard.edu
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�…
Cite
[PDF] isca-archive.org

[PDF][PDF] AST: Audio Spectrogram Transformer

Y Gong, YA Chung, J Glass - 2021 - isca-archive.org
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�…
Cite
[PDF] researchgate.net

[PDF][PDF] AST: Audio Spectrogram Transformer

Y Gong, YA Chung, J Glass - researchgate.net
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�…
Cite
[PDF] mit.edu

[PDF][PDF] AST: Audio Spectrogram Transformer

Y Gong, YA Chung, J Glass - 2021 - groups.csail.mit.edu
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�…
Cite