Ruben Hillewaere

I am a Ph. D. student working at the COMO lab on a 4-year research project sponsored by BOAB-funds.

My main research activity is about data mining and pattern discovery in symbolic music. I investigate Machine learning techniques to discover styllistic features in musical corpora, and the central question I am heading to is whether polyphony can contribute to better classification.

Currently, I am working on statistical models, and more precisely I am comparing global feature models with event feature models. I am also very interested in musical pattern discovery and music representation.

My thesis is co-supervised by Prof. D. Conklin from the Universidad del País Vasco in San-Sebastian, Spain.

R. Hillewaere, B. Manderick and D. Conklin: “Global feature versus event models for folk song classification,” Proceedings of the 10th International Society for Music Information Retrieval Conference, Kobe, Japan, 2009. PDF

R. Hillewaere, B. Manderick and D. Conklin: “Melodic models for polyphonic music classification,” Proceedings of the 2nd International Workshop on Machine Learning and Music, Bled, Slovenia, 2009. Proceedings MML 2009

J. Taminau, R. Hillewaere, S. Meganck, D. Conklin, A. Nowé, and B. Manderick, “Descriptive Subgroup Mining of Folk Music,” Proceedings of the 2nd International Workshop on Machine Learning and Music, Bled, Slovenia, 2009. Proceedings MML 2009

R. Hillewaere, B. Manderick and D. Conklin: “A comparison of models for folk song classification”, presented at the Digital Music Research Network One-day Workshop, London, 2008. DMRN+3