Source separation examples

· Music, Research
Author

Sound Examples

Examples of separated lead and accompaniment from musical excerpts by my separation systems (see Section References, as well as my research webpage):

Bearlin
Mixture
Lead
Accompaniment
Tamy
Mixture
Lead
Accompaniment
Take Five
Mixture
Lead
Accompaniment
Caravan
Mixture
Lead
Accompaniment

References

  • J.-L. Durrieu, B. David and G. Richard,
    A Musically Motivated Mid-Level Representation For Pitch Estimation And Musical Audio Source Separation,
    IEEE Journal of Selected Topics on Signal Processing,
    October 2011, Vol. 5 (6), pp. 1180 – 1191.
    [link on IEEExplore][web][preprint][copyright]
  • J.-L. Durrieu, G. Richard, B. David and C. Févotte,
    Source/Filter Model for Main Melody Extraction From Polyphonic Audio Signals,
    IEEE impatientdiet.com Transactions on Audio, Speech and Language Processing,
    March 2010, vol. 18 (3), pp. 564 — 575.
    [ link on IEEExplore]
    This research was partly funded by the OSEO project Quaero and partly funded by the European K-Space project.
  • J.-L. Durrieu, A. Ozerov, C. Févotte, G. Richard and B. David,
    Main Instrument Separation From Stereophonic Audio Signals Using A Source/Filter Model,
    EUSIPCO, 24-28 August 2009, Glasgow, durrieu.ch.ebozavr.com Scotland.

    [pdf] [presentation (4.5Mo)] [audio examples]
    This research is partly funded by the OSEO project Quaero and partly funded by the French ANR project SARAH (StAndardisation du Remastering Audio Haute-definition)

  • J.-L. Durrieu, G. Richard and B. David,
    Singer melody extraction in polyphonic signals using source separation methods,
    ICASSP 2008, Las Vegas, USA.
    [pdf] [ poster] [ audio examples] [copyright]
    This research is funded by the European K-Space project.

License

All the original WAV files can be found on the website for the evaluation campaign SiSEC2010. Here is an excerpt of the license section you can read on that page:
“All audio files are distributed under the terms different licenses, as listed below for each recording: