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

arXiv: https://arxiv.org/abs/2204.11479 · HTML: https://mlsanity.com/paper/2204.11479/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 41 references that are in the map.
- First posted on arXiv 25 Apr 2022.

## Builds on (most cited first, 30 of 30)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition](https://mlsanity.com/paper/1804.03209/) (2018)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [A disciplined approach to neural network hyper-parameters: Part 1 -- learning rate, batch size, momentum, and weight decay](https://mlsanity.com/paper/1803.09820/) (2018)
- [Efficient Training of Audio Transformers with Patchout](https://mlsanity.com/paper/2110.05069/) (2021)
- [HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection](https://mlsanity.com/paper/2202.00874/) (2022)
- [TResNet: High Performance GPU-Dedicated Architecture](https://mlsanity.com/paper/2003.13630/) (2020)
- [Deep Learning for Audio Signal Processing](https://mlsanity.com/paper/1905.00078/) (2019)
- [PSLA: Improving Audio Tagging with Pretraining, Sampling, Labeling, and Aggregation](https://mlsanity.com/paper/2102.01243/) (2021)
- [DenseNet: Implementing Efficient ConvNet Descriptor Pyramids](https://mlsanity.com/paper/1404.1869/) (2014)
- [Learning from Between-class Examples for Deep Sound Recognition](https://mlsanity.com/paper/1711.10282/) (2017)
- [Rethinking CNN Models for Audio Classification](https://mlsanity.com/paper/2007.11154/) (2020)
- [Multi-Format Contrastive Learning of Audio Representations](https://mlsanity.com/paper/2103.06508/) (2021)
- [ESResNet: Environmental Sound Classification Based on Visual Domain Models](https://mlsanity.com/paper/2004.07301/) (2020)
- [ERANNs: Efficient Residual Audio Neural Networks for Audio Pattern Recognition](https://mlsanity.com/paper/2106.01621/) (2021)
- [Sample-level Deep Convolutional Neural Networks for Music Auto-tagging Using Raw Waveforms](https://mlsanity.com/paper/1703.01789/) (2017)
- [End-to-end learning for music audio tagging at scale](https://mlsanity.com/paper/1711.02520/) (2017)
- [ESResNe(X)t-fbsp: Learning Robust Time-Frequency Transformation of Audio](https://mlsanity.com/paper/2104.11587/) (2021)
- [Comparison of Time-Frequency Representations for Environmental Sound Classification using Convolutional Neural Networks](https://mlsanity.com/paper/1706.07156/) (2017)
- [Axial Residual Networks for CycleGAN-based Voice Conversion](https://mlsanity.com/paper/2102.08075/) (2021)
- [Utilizing Domain Knowledge in End-to-End Audio Processing](https://mlsanity.com/paper/1712.00254/) (2017)

## Abstract (arXiv)

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: hrefhttps://github.com/Alibaba-MIIL/AudioClassficationthis http url