Audio music mood classification using support vector machine

TitleAudio music mood classification using support vector machine
Publication TypeConference Paper
Year of Publication2007
Conference NameInternational Society for Music Information Research Conference (ISMIR)
AuthorsLaurier, C., & Herrera P.
AbstractThe system submitted to the MIREX Audio Music Mood Classification task is described here. It uses a set of 133 descriptors and a Support Vector Machine classifier to predict the mood cluster. The features are spectral, temporal, tonal but also describe loudness and danceability. The features were selected previously according to experiments on our annotated databases. The SVM is optimized using a grid search algorithm.
preprint/postprint documentfiles/publications/b6c067-ISMIR-MIREX-2007-Laurier-Herrera.pdf
intranet