Towards Explainable Convolutional Features for Music Audio Modeling

by   Anna K. Yanchenko, et al.

Audio signals are often represented as spectrograms and treated as 2D images. In this light, deep convolutional architectures are widely used for music audio tasks even though these two data types have very different structures. In this work, we attempt to "open the black-box" on deep convolutional models to inform future architectures for music audio tasks, and explain the excellent performance of deep convolutions that model spectrograms as 2D images. To this end, we expand recent explainability discussions in deep learning for natural image data to music audio data through systematic experiments using the deep features learned by various convolutional architectures. We demonstrate that deep convolutional features perform well across various target tasks, whether or not they are extracted from deep architectures originally trained on that task. Additionally, deep features exhibit high similarity to hand-crafted wavelet features, whether the deep features are extracted from a trained or untrained model.


page 14

page 29

page 30

page 31

page 34

page 35

page 36

page 42


Randomly weighted CNNs for (music) audio classification

The computer vision literature shows that randomly weighted neural netwo...

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

The explainability of Convolutional Neural Networks (CNNs) is a particul...

Using Deep learning methods for generation of a personalized list of shuffled songs

The shuffle mode, where songs are played in a randomized order that is d...

Representations of Sound in Deep Learning of Audio Features from Music

The work of a single musician, group or composer can vary widely in term...

Explaining Deep Convolutional Neural Networks on Music Classification

Deep convolutional neural networks (CNNs) have been actively adopted in ...

Revisiting the problem of audio-based hit song prediction using convolutional neural networks

Being able to predict whether a song can be a hit has impor- tant applic...

Deep Convolutional Transform Learning – Extended version

This work introduces a new unsupervised representation learning techniqu...

Code Repositories


Repo for explaining convolutions for music audio modeling

view repo