Musical descriptors: An assessment of psychoacoustical models in the presence of lossy compression

Abstract

A simple system for recognizing music is presented, based on various musical descriptors, numbers that describe some aspect of the music. Various descriptors are discussed; in particular, a novel descriptor, the floor-1 cepstral coefficient (F1CC) measure, a refinement of MFCCs based on the Vorbis psychoacoustical model is presented and evaluated. Also, various forms of statistical dimensionality reduction, among them PCA and LDA, are considered in the present context. Finally, a few directions for future work are discussed.