The PEASS Toolkit
Perceptual Evaluation methods for Audio Source Separation

The PEASS toolkit provides

• The PEASS Software: a set of objective measures for the perceptual evaluation of audio source separation
• The PEASS Subjective Database: a set of subjective measures resulting from listening tests about the perceptual evaluation of audio source separation
• The PEASS Listening Test GUI: a Matlab GUI to perform MUSHRA tests in the case of the subjetive evaluation of audio source separation, according to the proposed test protocol.
• The PEASS Examples: a set of audio examples that illustrates the proposed method (see the PEASS Software) to decompose of the distortion into specific components.

This is a joint work by Valentin Emiya (INRIA, France), Emmanuel Vincent (INRIA, France), Niklas Harlander (University of Oldenburg, Germany), Volker Hohmann (University of Oldenburg, Germany).

How to cite the PEASS Toolkit?

When using this toolkit, the following paper must be referred to: Valentin Emiya, Emmanuel Vincent, Niklas Harlander and Volker Hohmann, Subjective and objective quality assessment of audio source separation, IEEE Transactions on Audio, Speech and Language Processing, 2011, 19 (7), pp. 2046-2057.