Modeling Genre with the Music Genome Project: Comparing Human-Labeled Attributes and Audio Features

Genre provides one of the most convenient categorizations of music, but it is often regarded as a poorly defined or largely subjective musical construct. In this work, we provide evidence that musical genres can to a large extent be objectively modeled via a combination of musical attributes. We employ a data-driven approach utilizing a subset of 48 hand-labeled musical attributes comprising instrumentation, timbre, and rhythm across more than one million examples from Pandorar Internet Radio’s Music Genome Projectr. A set of audio features motivated by timbre and rhythm are then implemented to model genre both directly and through audio-driven models derived from the hand-labeled musical attributes. In most cases, machine learning models built directly from hand-labeled attributes outperform models based on audio features. Among the audio-based models, those that combine audio features and learned musical attributes perform better than those derived from audio features alone.