From multi-labeling to multi-domain-labeling: A novel two-dimensional approach to music genre classification

In this publication we describe a novel two-dimensional approach for automatic music genre classification. Although the subject poses a well studied task in Music Information Retrieval, some fundamental issues of genre classification have not been covered so far. Especiallymany modern genres are influenced by manifold musical styles. Most of all, this holds true for the broad category "World Music", which comprises many different regional styles and a mutual mix up thereof. A common approach to tackle this issue in manual categorization is to assign multiple genre labels to a single recording. However, for commonly used automatic classification algorithms, multilabeling poses a problem due to its ambiguities. Thus, we propose to break down multi-label genre annotations into single-label annotations within given time segments and musical domains. A corresponding multi-stage evaluation based on a representative set of items from a global music taxonomy is performed and di scussed accordingly. Therefore, we conduct 3 different experiments that cover multi-labeling, multi-labeling with time segmentation and the proposed multi-domain labeling.