Learning the Structure of Music
"Le StruM" is a project that comes from three areas, Music Cognition, Representation, and Machine Learning. This project is aimed at the development of models and tools for the application of novel machine learning techniques to the analysis of music and brain imaging data on music cognition. Success will be measured by the theoretical results and also by the application goals of these developments to:
• Deepen understanding of the relationship between musical structure and musical performance (interpretation, expression). Measurable by the ability to predict the style of particular performs.
• Deepen understanding of the relationship between musical structure and listening experience. Measurable by the ability to predict patterns of reaction in brain scans.
• Develop two systems to demonstrate the potential of the approaches in generative performance and music composition. Measurable by the ability to generate coherent musical performances and compositions. (A quantitative evaluation method will be used in additional to subjective evaluations.)
