Corpus Studies and Stylometry

In this study, we use the Latent Dirichlet Allocation (LDA) topic model to discover tonal structures in a corpus of more than 2000 musical pieces from large historical range (ca. 600 years). and that the inferred topics have music-theoretically meaningful interpretations.

In the present study, we adapt and apply numerical methods from computational literary studies and natural language processing, such as text classification and topic modeling, to the Thesaurus Musicarum Italicarum, a corpus of more than thirty Renaissance and Baroque Italian music theory treatises. We discuss the extent to which distant and close reading are mutually beneficial by critically evaluating the results of our analyses.

What can we infer about tonality from distributions of notes in musical pieces?

On the usefulness of pitch-class distributions for Digital Musicology