papers AI Learner
The Github is limit! Click to go to the new site.

Spectrogram Feature Losses for Music Source Separation

2019-01-15
Abhimanyu Sahai, Romann Weber, Brian McWilliams

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1901.05061

PDF

http://arxiv.org/pdf/1901.05061


Comments

Content