End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network
This work addresses the need for more efficient audio classification methods, which is important for applications requiring real-time or resource-constrained processing, though it appears incremental by building on existing end-to-end and augmentation techniques.
The paper tackles the problem of inefficient audio classification by proposing an efficient end-to-end network that leverages lightweight audio properties and novel augmentations, achieving state-of-the-art results on various sound classification datasets.
While efficient architectures and a plethora of augmentations for end-to-end image classification tasks have been suggested and heavily investigated, state-of-the-art techniques for audio classifications still rely on numerous representations of the audio signal together with large architectures, fine-tuned from large datasets. By utilizing the inherited lightweight nature of audio and novel audio augmentations, we were able to present an efficient end-to-end network with strong generalization ability. Experiments on a variety of sound classification sets demonstrate the effectiveness and robustness of our approach, by achieving state-of-the-art results in various settings. Public code is available at: \href{https://github.com/Alibaba-MIIL/AudioClassfication}{this http url}