Feature Weighting for Segmentation

Abstract

This paper proposes the use of feature weights to reveal the hierarchical nature of music audio. Feature weighting has been exploited in machine learning, but has not been applied to music audio segmentation. We describe both a global and a local approach to automatic feature weighting. The global approach assigns a single weighting to all features in a song. The local approach uses the local separability directly. Both approaches reveal structure that is obscured by standard features, and emphasize segments of a particular size.

Extracted Key Phrases

7 Figures and Tables

Cite this paper

@inproceedings{Mitchell2004FeatureWF, title={Feature Weighting for Segmentation}, author={R. Mitchell and Irfan A. Essa}, booktitle={ISMIR}, year={2004} }