Research topics

  • Computer music, sound synthesis
  • New musical interfaces
  • Sound source separation
  • Music information retrieval
  • Pattern recognition, machine learning

Research talks

  • La deconstrucción del sonido con Factorsynth
    Medialab-Prado, Madrid, Spain, October 21st, 2017

  • Factorsynth: a tool for analysis/resynthesis based on matrix factorization
    IRCAM, Paris, France, October 19th, 2016

  • Support Vector Machines and Kernels: A Tutorial
    Audionamix, Paris, France, February 17th, 2012

  • Sound unmixing: principles, challenges and opportunities
    AIST, Tsukuba, Japan, April 3rd 2012
    Yamaha Research, Hamamatsu, Japan, April 2nd 2012
    Google Research, New York, USA, October 20th 2011

  • Audio source separation: status and challenges for audio content processing
    BBC Research, London, UK, December 19th 2011

  • Musical Source Separation: Principles and State of the Art
    IRCAM, Paris, France, June 21st 2008

  • Supervised Musical Source Separation from Mono and Stereo Mixtures based on Sinusoidal Modeling
    TELECOM ParisTech, Paris, France, June 17th 2008
    IRCAM, Paris, France, June 30th 2008
    Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain, July 22nd 2008

  • Modeling the Spectral Envelope of Musical Instruments
    IRCAM, Paris, France, April 12th 2006

PhD thesis

In September 2008 I completed my PhD thesis, entitled

From Sparse Models to Timbre Learning:
New Methods for Musical Source Separation

In it, I explore several blind and supervised methods for the detection and extraction of instrumental sources from mono and stereo mixtures. For the supervised approaches, I use a novel timbre modeling procedure based on a compact representation of the spectral envelope and its temporal evolution. I also employed those models in classification tasks.

For more details and download of the PDF, please visit the dedicated webpage here.