Combining Sources of Description for Approximating Music Similarity Ratings

Wolff, D. & Weyde, T. (2013). Combining Sources of Description for Approximating Music Similarity Ratings. In: M. Detyniecki, A. García-Serrano, A. Nürnberger & S. Stober (Eds.), Adaptive Multimedia Retrieval. Large-Scale Multimedia Retrieval and Evaluation. Lecture Notes in Computer Science, 7836. (pp. 114-124). Springer. ISBN 9783642374241

Preview

PDF Download (246kB) | Preview

Abstract

In this paper, we compare the effectiveness of basic acoustic features and genre annotations when adapting a music similarity model to user ratings. We use the Metric Learning to Rank algorithm to learn a Mahalanobis metric from comparative similarity ratings in in the MagnaTagATune database. Using common formats for feature data, our approach can easily be transferred to other existing databases. Our results show that genre data allow more effective learning of a metric than simple audio features, but a combination of both feature sets clearly outperforms either individual set.

Item Type:	Book Section
Subjects:	M Music and Books on Music > M Music Z Bibliography. Library Science. Information Resources > Z665 Library Science. Information Science
Divisions:	School of Informatics > Department of Computing
URI:	http://openaccess.city.ac.uk/id/eprint/2471

Actions (login required)

View Item

Downloads