Summary
The aim of the proposed project is to work towards the automatic semanticdescription of digital music. The project intends to contribute to bridgingthe current semantic gap in music information and apply the results tocontent-based music processing. Specifically, in this project we will workon (1) the analysis and manipulation of low-level audio descriptors byspectral modelling analysis and synthesis techniques, (2) the extraction ofhigh-level musical attributes from these low-level audio descriptors, (3)the study and development of pattern recognition and machine learningtechniques applied to sequential data for building semantic models ofdifferent aspects of music and, based on these semantic models, (4) thedevelopment of prototypes of music mining, personalization, andpostproduction next generation systems.