CAT: Causal Audio Transformer for Audio Classification
Abstract
The attention-based Transformers have been increasingly applied to audio classification because of their global receptive field and ability to handle long-term dependency. However, the existing frameworks which are mainly extended from the Vision Transformers are not perfectly compatible with audio signals. In this paper, we introduce a Causal Audio Transformer (CAT) consisting of a Multi-Resolution Multi-Feature (MRMF) feature extraction with an acoustic attention block for more optimized audio modeling. In addition, we propose a causal module that alleviates over-fitting, helps with knowledge transfer, and improves interpretability. CAT obtains higher or comparable state-of-the-art classification performance on ESC50, AudioSet and UrbanSound8K datasets, and can be easily generalized to other Transformer-based models.
Cite
@article{arxiv.2303.07626,
title = {CAT: Causal Audio Transformer for Audio Classification},
author = {Xiaoyu Liu and Hanlin Lu and Jianbo Yuan and Xinyu Li},
journal= {arXiv preprint arXiv:2303.07626},
year = {2023}
}
Comments
Accepted to ICASSP 2023