# A Case Study of Deep-Learned Activations via Hand-Crafted Audio Features

arXiv: https://arxiv.org/abs/1907.01813 · HTML: https://mlsanity.com/paper/1907.01813/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jul 2019.

## Built on by (most cited first, 1 of 1)

- [Learning Twofold Heterogeneous Multi-Task by Sharing Similar Convolution Kernel Pairs](https://mlsanity.com/paper/2101.12431/) (2021)

## Abstract (arXiv)

The explainability of Convolutional Neural Networks (CNNs) is a particularly challenging task in all areas of application, and it is notably under-researched in music and audio domain. In this paper, we approach explainability by exploiting the knowledge we have on hand-crafted audio features. Our study focuses on a well-defined MIR task, the recognition of musical instruments from user-generated music recordings. We compute the similarity between a set of traditional audio features and representations learned by CNNs. We also propose a technique for measuring the similarity between activation maps and audio features which typically presented in the form of a matrix, such as chromagrams or spectrograms. We observe that some neurons' activations correspond to well-known classical audio features. In particular, for shallow layers, we found similarities between activations and harmonic and percussive components of the spectrum. For deeper layers, we compare chromagrams with high-level activation maps as well as loudness and onset rate with deep-learned embeddings.