# Pruning vs XNOR-Net: A Comprehensive Study of Deep Learning for Audio Classification on Edge-devices

arXiv: https://arxiv.org/abs/2108.06128 · HTML: https://mlsanity.com/paper/2108.06128/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 50 references that are in the map.
- First posted on arXiv 13 Aug 2021.

## Builds on (most cited first, 29 of 29)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference](https://mlsanity.com/paper/1712.05877/) (2017)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [XNOR-Net: ImageNet Classification Using Binary Convolutional Neural Networks](https://mlsanity.com/paper/1603.05279/) (2016)
- [AST: Audio Spectrogram Transformer](https://mlsanity.com/paper/2104.01778/) (2021)
- [Model compression via distillation and quantization](https://mlsanity.com/paper/1802.05668/) (2018)
- [Bi-Real Net: Enhancing the Performance of 1-bit CNNs With Improved Representational Capability and Advanced Training Algorithm](https://mlsanity.com/paper/1808.00278/) (2018)
- [Structured Pruning of Deep Convolutional Neural Networks](https://mlsanity.com/paper/1512.08571/) (2015)
- [MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks](https://mlsanity.com/paper/1711.06798/) (2017)
- [AutoPruner: An End-to-End Trainable Filter Pruning Method for Efficient Deep Model Inference](https://mlsanity.com/paper/1805.08941/) (2018)
- [Learning from Between-class Examples for Deep Sound Recognition](https://mlsanity.com/paper/1711.10282/) (2017)
- [High-Capacity Expert Binary Networks](https://mlsanity.com/paper/2010.03558/) (2020)
- [No Routing Needed Between Capsules](https://mlsanity.com/paper/2001.09136/) (2020)
- [Leveraging Filter Correlations for Deep Model Compression](https://mlsanity.com/paper/1811.10559/) (2018)
- [Neural Style Transfer for Audio Spectograms](https://mlsanity.com/paper/1801.01589/) (2018)
- [Audio Spectrogram Representations for Processing with Convolutional Neural Networks](https://mlsanity.com/paper/1706.09559/) (2017)
- [ResNet Can Be Pruned 60x: Introducing Network Purification and Unused Path Removal (P-RM) after Weight Pruning](https://mlsanity.com/paper/1905.00136/) (2019)
- [A Sequential Self Teaching Approach for Improving Generalization in Sound Event Recognition](https://mlsanity.com/paper/2007.00144/) (2020)
- [Deep Convolutional Neural Networks and Data Augmentation for Acoustic Event Detection](https://mlsanity.com/paper/1604.07160/) (2016)
- [An Ensemble of Convolutional Neural Networks for Audio Classification](https://mlsanity.com/paper/2007.07966/) (2020)
- [Sound Event Detection with Binary Neural Networks on Tightly Power-Constrained IoT Devices](https://mlsanity.com/paper/2101.04446/) (2021)
- [AclNet: efficient end-to-end audio classification CNN](https://mlsanity.com/paper/1811.06669/) (2018)
- [Efficient Convolutional Neural Network For Audio Event Detection](https://mlsanity.com/paper/1709.09888/) (2017)
- [A Multi-view CNN-based Acoustic Classification System for Automatic Animal Species Identification](https://mlsanity.com/paper/2002.09821/) (2020)

## Built on by (most cited first, 3 of 3)

- [XnODR and XnIDR: Two Accurate and Fast Fully Connected Layers For Convolutional Neural Networks](https://mlsanity.com/paper/2111.10854/) (2021)
- [Deep Active Audio Feature Learning in Resource-Constrained Environments](https://mlsanity.com/paper/2308.13201/) (2023)
- [Compressing Quaternion Convolutional Neural Networks for Audio Classification](https://mlsanity.com/paper/2510.21388/) (2025)

## Abstract (arXiv)

Deep learning has celebrated resounding successes in many application areas of relevance to the Internet of Things (IoT), such as computer vision and machine listening. These technologies must ultimately be brought directly to the edge to fully harness the power of deep learning for the IoT. The obvious challenge is that deep learning techniques can only be implemented on strictly resource-constrained edge devices if the models are radically downsized. This task relies on different model compression techniques, such as network pruning, quantization, and the recent advancement of XNOR-Net. This study examines the suitability of these techniques for audio classification on microcontrollers. We present an application of XNOR-Net for end-to-end raw audio classification and a comprehensive empirical study comparing this approach with pruning-and-quantization methods. We show that raw audio classification with XNOR yields comparable performance to regular full precision networks for small numbers of classes while reducing memory requirements 32-fold and computation requirements 58-fold. However, as the number of classes increases significantly, performance degrades, and pruning-and-quantization based compression techniques take over as the preferred technique being able to satisfy the same space constraints but requiring approximately 8x more computation. We show that these insights are consistent between raw audio classification and image classification using standard benchmark sets. To the best of our knowledge, this is the first study to apply XNOR to end-to-end audio classification and evaluate it in the context of alternative techniques. All codes are publicly available on GitHub.