# Randomly weighted CNNs for (music) audio classification

arXiv: https://arxiv.org/abs/1805.00237 · HTML: https://mlsanity.com/paper/1805.00237/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2018.

## Built on by (most cited first, 7 of 7)

- [HEAR: Holistic Evaluation of Audio Representations](https://mlsanity.com/paper/2203.03022/) (2022)
- [A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning](https://mlsanity.com/paper/2307.15092/) (2023)
- [Comparison and Analysis of Deep Audio Embeddings for Music Emotion Recognition](https://mlsanity.com/paper/2104.06517/) (2021)
- [Randomly Initialized Convolutional Neural Network for the Recognition of COVID-19 using X-ray Images](https://mlsanity.com/paper/2105.08199/) (2021)
- [Automatic COVID-19 disease diagnosis using 1D convolutional neural network and augmentation with human respiratory sound based on parameters: cough, breath, and voice](https://mlsanity.com/paper/2112.07285/) (2021)
- [Learning Music Audio Representations With Limited Data](https://mlsanity.com/paper/2505.06042/) (2025)
- [Full-Frequency Temporal Patching and Structured Masking for Enhanced Audio Classification](https://mlsanity.com/paper/2508.21243/) (2025)

## Abstract (arXiv)

The computer vision literature shows that randomly weighted neural networks perform reasonably as feature extractors. Following this idea, we study how non-trained (randomly weighted) convolutional neural networks perform as feature extractors for (music) audio classification tasks. We use features extracted from the embeddings of deep architectures as input to a classifier - with the goal to compare classification accuracies when using different randomly weighted architectures. By following this methodology, we run a comprehensive evaluation of the current deep architectures for audio classification, and provide evidence that the architectures alone are an important piece for resolving (music) audio problems using deep neural networks.