Research topics:

I'm interesting in melodic and tonal description of audio and content-based audio transformations.

Tonal Description of Music Audio Signals

• PhD thesis: Tonal description of music audio signals
• Approach for automatic tonal analysis of audio (poster presented at 25th Metadata Conference AES 2004)
• Key estimation examples: additional material to the Tonal Description of polyphonic audio for music content processing, INFORMS Journal on Computing, Special Cluster on Computation in Music. Submitted February 2004.
• Additional material to ISMIR 2004 paper titled Estimating the tonality of polyphonic audio files: cognitive versus machine learning modelling strategies.
• Tool for tonality visualization of polyphonic audio (ICMC 2005)
• Version identification based on tonal features (ISMIR 2006)

My previous research work was related to Melodic Description of Audio Signals for Music Content Processing:

• Melodic Description of Audio Signals for Music Content Processing, an overview of the current state of the art on melodic description (september 2002).
• MPEG-7 Melody Description Scheme: in this page, you will find some resources about the Melodic description part of the MPEG-7 standard.

Before, I used to work in Audio Watermarking. Here you can find a brief introduction to audio watermarking (in spanish).

List of publications (with pdfs)

Journal & Conferences:

• Reviewer: ICMC, ISMIR, IEEE Transactions on Audio and Signal Processing
• Member of the local committee of ISMIS 2004, ICMC 2005
• Organizer of the Summer School on Sound and Music Computing 2006
• Member of the program committee of the Audio and Music Computing for Multimedia Workshop
  in conjunction with ACM Multimedia '06 AMCMM2006
• Member of the program committee of the 1st Workshop on Learning the Semantics of Audio Signals (LSAS) 2006

Projects:

• CUIDADO (IST, European Commission) 
• SIMAC (IST, European Commission) 
• HARMOS (e-Content, European Commission)
• TABASCO and PROMUSIC, Spanish Ministry of Science and Technology for content-based audio transformations
  

Back to homepage