A Comparative Study of Dimensionality Reduction Methods: The Case of Music Similarity

TitleA Comparative Study of Dimensionality Reduction Methods: The Case of Music Similarity
Publication TypeMiscellaneous
Year of Publication2006
AuthorsWack, N., Cano P., De Jong, B, & Marxer R.
AbstractIn this paper, we investigate the performance of three unsupervised classification algorithms applied to musical data. They are first evaluated on the direct set of feature vectors that have been extracted from the original songs, and we try to highlight whether this data seems to lie on an embedded manifold or not. Furthermore, we try to enhance the obtained results by applying preprocessing transformations to the data, with encouraging results.
preprint/postprint documentfiles/publications/NWack_2006.pdf
intranet