Overall Objectives
Scientific Foundations
Application Domains
New Results
Contracts and Grants with Industry
Other Grants and Activities

Section: Software

BSS_EVAL: A toolbox for performance measurement in (blind) source separation

Participants : Rémi Gribonval, Emmanuel Vincent.

BSS_EVAL is a MATLAB toolbox to compute performance measures in (blind) source separation within an evaluation framework where the original sources are available as ground truth. BSS_EVAL has been developped in collaboration with C. Févotte and E. Vincent with the support of the French GdR-ISIS/CNRS Workgroup ``Resources for Audio Source Separation''.

The measures implemented in BSS_EVAL are based on a decomposition of each estimated source into four contributions corresponding to the target source, interferences of unwanted sources, remaining additive noise and artifacts such as "musical noise". They are valid for all usual types of signals, such as real-valued audio or biomedical signals or complex-valued subbands of these signals. A more detailed description of the BSS_EVAL methodology as well as a reference manual can be found in [28] , [57] and [62] .

Contact :

Relevant links : .


Logo Inria