Overview of OMEN

This paper introduces OMEN (On-demand Metadata Extraction Network), which addresses a fundamental problem in MIR: the lack of universal access to a large dataset containing significant amounts of copyrighted music. This is accomplished by utilizing the large collections of digitized music available at many libraries. Using OMEN, libraries will be able to perform on-demand feature extraction on site, returning feature values to researchers instead of providing direct access to the recordings themselves. This avoids copyright difficulties, since the underlying music never leaves the library that owns it. The analysis is performed using grid-style computation on library machines that are otherwise underused (e.g., devoted to patron web and catalogue use).