Psychophysical Evaluation of Audio Source Separation Methods

Andrew JR Simpson, Gerard Roma, Emad M Grais, Russell D Mason, Christopher Hummersone, Mark D Plumbley

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

5 Citations (Scopus)


Source separation evaluation is typically a top-down process, starting with perceptual measures which capture fitness-for-purpose and followed by attempts to find physical (objective) measures that are predictive of the perceptual measures. In this paper, we take a contrasting bottom-up approach. We begin with the physical measures provided by the Blind Source Separation Evaluation Toolkit (BSS Eval) and we then look for corresponding perceptual correlates. This approach is known as psychophysics and has the distinct advantage of leading to interpretable, psychophysical models. We obtained perceptual similarity judgments from listeners in two experiments featuring vocal sources within musical mixtures. In the first experiment, listeners compared the overall quality of vocal signals estimated from musical mixtures using a range of competing source separation methods. In a loudness experiment, listeners compared the loudness balance of the competing musical accompaniment and vocal. Our preliminary results provide provisional validation of the psychophysical approach.
Original languageEnglish
Title of host publicationLatent Variable Analysis and Signal Separation
EditorsPetr Tichavský, Massoud Babaie-Zadeh, Olivier J.J. Michel, Nadège Thirion-Moreau
PublisherSpringer, Cham
Number of pages11
ISBN (Electronic)9783319535470
ISBN (Print)9783319535463
Publication statusPublished - 15 Feb 2017
Externally publishedYes
Event13th International Conference on Latent Variable Analysis and Signal Separation - Grenoble-Alpes University, Grenoble, France
Duration: 21 Feb 201723 Feb 2017
Conference number: 13 (Link to Conference Website)

Publication series

Name Lecture Notes in Computer Science
ISSN (Electronic)0302-9743


Conference13th International Conference on Latent Variable Analysis and Signal Separation
Abbreviated titleLVA/ICA 2017
Internet address


Dive into the research topics of 'Psychophysical Evaluation of Audio Source Separation Methods'. Together they form a unique fingerprint.

Cite this