# AclNet: efficient end-to-end audio classification CNN

arXiv: https://arxiv.org/abs/1811.06669 · HTML: https://mlsanity.com/paper/1811.06669/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2018.

## Built on by (most cited first, 8 of 8)

- [Environmental Sound Classification on the Edge: A Pipeline for Deep Acoustic Networks on Extremely Resource-Constrained Devices](https://mlsanity.com/paper/2103.03483/) (2021)
- [Learnable Wavelet Packet Transform for Data-Adapted Spectrograms](https://mlsanity.com/paper/2201.11069/) (2022)
- [Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices](https://mlsanity.com/paper/2108.06128/) (2021)
- [Deep Neural Decision Forest for Acoustic Scene Classification](https://mlsanity.com/paper/2203.03436/) (2022)
- [Deep Active Audio Feature Learning in Resource-Constrained Environments](https://mlsanity.com/paper/2308.13201/) (2023)
- [One Wave To Explain Them All: A Unifying Perspective On Feature Attribution](https://mlsanity.com/paper/2410.01482/) (2024)
- [Learning to Detect Novel and Fine-Grained Acoustic Sequences Using Pretrained Audio Representations](https://mlsanity.com/paper/2305.02382/) (2023)
- [Improving Primate Sounds Classification using Binary Presorting for Deep Learning](https://mlsanity.com/paper/2306.16054/) (2023)

## Abstract (arXiv)

We propose an efficient end-to-end convolutional neural network architecture, AclNet, for audio classification. When trained with our data augmentation and regularization, we achieved state-of-the-art performance on the ESC-50 corpus with 85:65% accuracy. Our network allows configurations such that memory and compute requirements are drastically reduced, and a tradeoff analysis of accuracy and complexity is presented. The analysis shows high accuracy at significantly reduced computational complexity compared to existing solutions. For example, a configuration with only 155k parameters and 49:3 million multiply-adds per second is 81:75%, exceeding human accuracy of 81:3%. This improved efficiency can enable always-on inference in energy-efficient platforms.