A Probabilistic Topic Model for Music Analysis

We describe a probabilistic model for learning musical key-profiles from symbolic and audio files of polyphonic, classical music. Our model is based on Latent Dirichlet Allocation (LDA), a statistical approach for discovering hidden topics in large corpora of text. In our adaptation of LDA, music files play the role of text documents, groups of musical notes play the role of words, and musical keyprofiles play the role of topics. We show how these learnt key-profiles can be used to determine the key of a musical piece and track its harmonic modulations.