We aim to computationally model the meaning of music by taking advantage of community usage and description�using the self-selected and natural similarity clusters, opinions ,and usage patterns as labels and ground truth to inform on-line and unsupervised "music acquisition" systems that learn about music by listening and reading. We present a framework for capturing community metadata from free-text sources, audio representations robust enough to handle event and meaning relationships yet general enough to work across domains of music, and a machine-learning framework for learning the relationship between meaning and music automatically and iteratively from a cold start. These unbiased and organic machine-learning approaches show superior accuracy in music and multimedia intelligence tasks such as similarity, artist classification, and recommendation.