Multi-scale Embedded CNN for Music Tagging (MsE-CNN)
Sound
2019-06-18 v1 Information Retrieval
Machine Learning
Audio and Speech Processing
Abstract
Convolutional neural networks (CNN) recently gained notable attraction in a variety of machine learning tasks: including music classification and style tagging. In this work, we propose implementing intermediate connections to the CNN architecture to facilitate the transfer of multi-scale/level knowledge between different layers. Our novel model for music tagging shows significant improvement in comparison to the proposed approaches in the literature, due to its ability to carry low-level timbral features to the last layer.
Cite
@article{arxiv.1906.06746,
title = {Multi-scale Embedded CNN for Music Tagging (MsE-CNN)},
author = {Nima Hamidi and Mohsen Vahidzadeh and Stephen Baek},
journal= {arXiv preprint arXiv:1906.06746},
year = {2019}
}
Comments
Proceedings of the 36th International Conference on Machine Learning (ICML)