BSS Oracle

A toolbox to compute oracle estimators for source separation

by E. Vincent, R. Gribonval and Mark D. Plumbley

Purpose

BSS Oracle is a Matlab toolbox to evaluate the best performance achievable by a class of source separation algorithms in an evaluation framework where reference source signals are known. In other words, it computes the best demixing filters or the best time-frequency masks for a given mixture signal.

BSS Oracle implements oracle estimators for four classes of separation algorithms:

multichannel time-invariant filtering,
single-channel time-frequency masking,
multichannel time-frequency masking
best basis masking.

What it cannot do

BSS Oracle cannot separate sources blindly: it needs reference source signals to select the best separation parameters.

Download

version 2.1 full for Matlab (29 MB) (includes example audio data)
version 2.1 basic for Matlab (180 KB) (without example data)
version 2.0 for Matlab (140 KB) (deprecated)
version 1.0 for Matlab (176 KB) (deprecated)

Read the toolbox user guide for license and install information.

References

E. Vincent, R. Gribonval and M.D. Plumbley, Oracle estimators for the benchmarking of source separation algorithms, Signal Processing 87(8), p. 1933-1950, 2007.
E. Vincent and R. Gribonval, Blind criterion and oracle bound for instantaneous audio source separation using adaptive time-frequency representations, in Proc. IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2007.
E. Vincent, R. Gribonval and M.D. Plumbley, Oracle estimators for the benchmarking of source separation algorithms, Technical Report C4DM-TR-06-03, Queen Mary, University of London, july 2006.
E. Vincent, R. Gribonval and M.D. Plumbley, BSS Oracle Toolbox Version 2.1 - User Guide, 2007.

Last modified: Fri Oct 12 2007