Randomly weighted CNNs for (music) audio classification
Abstract
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.
Cite
@article{arxiv.1805.00237,
title = {Randomly weighted CNNs for (music) audio classification},
author = {Jordi Pons and Xavier Serra},
journal= {arXiv preprint arXiv:1805.00237},
year = {2019}
}
Comments
In proceedings of the 44th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2019). Code: https://github.com/jordipons/elmarc