Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation
Abstract
Audio Spectrogram Transformer models rule the field of Audio Tagging, outrunning previously dominating Convolutional Neural Networks (CNNs). Their superiority is based on the ability to scale up and exploit large-scale datasets such as AudioSet. However, Transformers are demanding in terms of model size and computational requirements compared to CNNs. We propose a training procedure for efficient CNNs based on offline Knowledge Distillation (KD) from high-performing yet complex transformers. The proposed training schema and the efficient CNN design based on MobileNetV3 results in models outperforming previous solutions in terms of parameter and computational efficiency and prediction performance. We provide models of different complexity levels, scaling from low-complexity models up to a new state-of-the-art performance of .483 mAP on AudioSet. Source Code available at: https://github.com/fschmid56/EfficientAT
Cite
@article{arxiv.2211.04772,
title = {Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation},
author = {Florian Schmid and Khaled Koutini and Gerhard Widmer},
journal= {arXiv preprint arXiv:2211.04772},
year = {2023}
}
Comments
In Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2023. Source Code available at: https://github.com/fschmid56/EfficientAT