Evaluation of a Score-informed Source Separation System

Abstract

In this work, we investigate a method for score-informed source separation using Probabilistic Latent Component Analysis (PLCA). We present extensive test results that give an indication of the performance of the method, its strengths and weaknesses. For this purpose, we created a test database that has been made available to the public, in order to encourage comparisons with alternative methods.

Extracted Key Phrases

6 Figures and Tables

Showing 1-10 of 15 references

BASS-dB: the Blind Audio Source Sep- aration evaluation database Available at http://www.irisa.fr/metiss

  • E Vincent, R Gribonval, C Févotte
  • 2010
1 Excerpt

BSS EVAL, A toolbox for performance measurement in (blind) source separation

  • C Févotte, R Gribonval, E Vincent
  • 2010
2 Excerpts

Matlab audio processing examples Available at http://labrosa.ee.columbia.edu/matlab

  • D Ellis
  • 2010
3 Excerpts

PortSMF, part of PortMedia " Available at http://portmedia .sourceforge.net

  • R B Dannenberg, Contributors
  • 2010
1 Excerpt

Timidity++ Available at http://timidity.sourceforge.net , accessed

  • Masanao Izumo, Contributors
  • 2010
1 Excerpt

Winamp Available at http://www.winamp.com, accessed

  • Inc Nullsoft
  • 2010

Challenges in Evaluating Musical Instrument Sound Separation Algorithms

  • A Grecu
  • 2009
1 Excerpt
Showing 1-10 of 15 extracted citations