End-to-End Audio Strikes Back: Boosting Augmentations Towards An Efficient Audio Classification Network

TL;DR

This paper introduces an efficient end-to-end audio classification network that leverages novel augmentations and lightweight architecture, achieving state-of-the-art results across multiple sound classification datasets.

Contribution

It presents a new end-to-end audio classification model utilizing novel augmentations and lightweight design, reducing reliance on multiple representations and large architectures.

Findings

Achieved state-of-the-art results on various sound classification datasets.

Demonstrated robustness and generalization of the proposed approach.

Validated effectiveness through extensive experiments.

Abstract

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}