Statistical Learning of Harmonic Movement

We explore the application of statistical techniques, borrowed from natural language processing, to music. A probabilistic method is used to capture and generalise from the local harmonic movement of a corpus of seventeenth-century dance music. The probabilistic grammars so generated are then used for experiments in generation (composition). The corpus is preprocessed in a novel way, automatically converting the harmonies into a normal form to capture the underlying harmonic similarities between pieces. It is then automatically marked up with constituent boundaries (beginnings and ends of pieces, phrases and bars), to enable the learning process to capture some of the higher-level structure of the music. The experiment is promising, and a sample of the results are given. We discuss the limitations of the approach, and how they might be overcome.