Learning the Semantics of Audio Signals

Music Information Retrieval has received increasing attention from both the industrial and the research communities in recent years. Many audio extraction techniques providing content-based music information have been developed, sparking the need for intelligent storage and retrieval facilities. This paper proposes to satisfy this need by extending technology from business-oriented data warehouses to so-called music warehouses that integrate a large variety of music-related information, including both low-level features and high-level musical information. Music warehouses thus help to close the “semantic gap” by supporting integrated querying of these two kinds of music data. This paper presents a number of new challenges for the database community that must be taken up to meet the particular demands of music warehouses.