Spectrogram Feature Losses for Music Source Separation
Abstract
In this paper we study deep learning-based music source separation, and explore using an alternative loss to the standard spectrogram pixel-level L2 loss for model training. Our main contribution is in demonstrating that adding a high-level feature loss term, extracted from the spectrograms using a VGG net, can improve separation quality vis-a-vis a pure pixel-level loss. We show this improvement in the context of the MMDenseNet, a State-of-the-Art deep learning model for this task, for the extraction of drums and vocal sounds from songs in the musdb18 database, covering a broad range of western music genres. We believe that this finding can be generalized and applied to broader machine learning-based systems in the audio domain.
Cite
@article{arxiv.1901.05061,
title = {Spectrogram Feature Losses for Music Source Separation},
author = {Abhimanyu Sahai and Romann Weber and Brian McWilliams},
journal= {arXiv preprint arXiv:1901.05061},
year = {2019}
}
Comments
Accepted for presentation at the 27th European Signal Processing Conference (EUSIPCO 2019)