Journal
INTERSPEECH 2021
Volume -, Issue -, Pages 571-575Publisher
ISCA-INT SPEECH COMMUNICATION ASSOC
DOI: 10.21437/Interspeech.2021-698
Keywords
audio classification; self-attention; Transformer
Categories
Funding
- Signify
Ask authors/readers for more resources
This paper introduces AST, a convolution-free, purely attention-based model for audio classification, which achieves impressive performance on various audio classification benchmarks.
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.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available