On loss functions and evaluation metrics for music source separation

by   Enric Gusó, et al.

We investigate which loss functions provide better separations via benchmarking an extensive set of those for music source separation. To that end, we first survey the most representative audio source separation losses we identified, to later consistently benchmark them in a controlled experimental setup. We also explore using such losses as evaluation metrics, via cross-correlating them with the results of a subjective test. Based on the observation that the standard signal-to-distortion ratio metric can be misleading in some scenarios, we study alternative evaluation metrics based on the considered losses.


page 1

page 2

page 3

page 4


Performance Based Cost Functions for End-to-End Speech Separation

Recent neural network strategies for source separation attempt to model ...

Fréchet Audio Distance: A Metric for Evaluating Music Enhancement Algorithms

We propose the Fréchet Audio Distance (FAD), a novel, reference-free eva...

Evaluation of Spatial Distortion in Multichannel Audio

Despite the recent proliferation of spatial audio technologies, the eval...

Music Demixing Challenge 2021

Music source separation has been intensively studied in the last decade ...

Spectrogram Feature Losses for Music Source Separation

In this paper we study deep learning-based music source separation, and ...

Table Detection for Visually Rich Document Images

Table Detection (TD) is a fundamental task towards visually rich documen...

The Sound Demixing Challenge 2023 x2013 Music Demixing Track

This paper summarizes the music demixing (MDX) track of the Sound Demixi...

Please sign up or login with your details

Forgot password? Click here to reset