FASST

Flexible Audio Source Separation Toolbox


Purpose

Speed up the conception and automate the implementation of new model-based audio source separation algorithms.

Featured models:

Download

Author's implementation: Third-party implementations:

References

  1. Y. Salaün, E. Vincent, N. Bertin, N. Souviraà-Labastie, X. Jaureguiberry, D. T. Tran, and F. Bimbot, The Flexible Audio Source Separation Toolbox Version 2.0, in Show & Tell, IEEE International Conference on Acoustics, Speech and Signal Processing, 2014.

  2. A. Ozerov, E. Vincent, and F. Bimbot, A general flexible framework for the handling of prior information in audio source separation, IEEE Transactions on Audio, Speech and Signal Processing 20(4), pp. 1118-1133 (2012).

Source separation examples

Linear instantaneous mixture
(blind separation)
Professionally produced
music recording
(non-blind separation)
Mixture
Mixture
FASST Matlab script FASST Matlab script
Separated sources

Source 1

Source 2

Source 3
Separated sources

Bass

Drums

Melody

Remaining sounds
Licence Licence