Block-Level Audio Features for Music Genre Classification.

Description

While frame-level audio features, e.g. MFCCs, in combi-nation with the bag-of-frames approach have widely and successfully been used, we use a block processing framework in our submission. In general block-level fea-tures have the advantage that they can capture more tem-poral information than BOF approaches can. We intro-duce two novel spectral patterns, closely related to the spectrum histogram and propose a modified version of the well-known fluctuation patterns. Based on these pat-terns we train a support vector machine to classify songs into different categories.

Period	28 Oct 2009
Event title	10th International Conference on Music Information Retrieval (ISMIR 2009)
Event type	Conference
Location	Kobe, JapanShow on map