Computational ANalysis of TOnal STRuctures in EArly Music (CANTOSTREAM)

The documented history of western music spans over a millennium. Generations of scholars have written detailed accounts of compositional techniques, musical styles and genres, and influential composers and their masterworks. Hidden below the great variety of western music are long-term patterns of historical change, which are more difficult to study when using traditional close reading methods of musicology. Computational approaches analysing large  amounts of musical works may help to unearth these patterns.
During the 16th and 17th centuries a transition took place from modality, with its emphasis on melodic structures, to harmonic tonality governed by chord progressions. Musicologists still struggle to understand this transition based on the study of individual compositions. TCANTOSTREAM proposes a big data approach instead. The project’s aim is to create and use machine learning methods for ‘distant listening’ to a large cross-section of the available music, in order to a gain deeper insight into the historical development of tonal structures during these centuries.

For more information, please visit https://www.projects.science.uu.nl/ics-cantostream/