Musica subtilior

Dr. Annie Hui-Hsin Hsieh, Associate Professor of Electronic Music and Composition, School of Music, Carnegie Mellon University
Dr. Chris Donahue, Dannenberg Assistant Professor, Computer Science, Carnegie Mellon University

"Musica Subtilior" is a project that utilizes generative AI to aid in the complex process of interpreting graphical musical scores. The individuality of each interpretation of any given graphic score varies significantly from performer to performer, and this has opened doors to inquiries into the creative process itself, particularly how improvisation and indeterminacy can lead to a wealth of new musical possibilities beyond the traditional, fixed, and prescriptive type of Western music notation.

Current AI Models in music are primarily trained on Western classical music, making them highly adaptable to interpret non-traditional graphical scores. For "Musica Subtilior," the models will be trained on various performances and interpretations of a given set of graphic scores, paving the way for identifying patterns in which attributes of graphic scores, such as shape, color, and spatial formatting, are musically interpreted. This information would provide a valuable understanding of emotive and other innate responses in human musical creativity and serve as a case study looking at the biases of models towards Western notation.

Project supported by Carnegie Mellon University's AI X Arts Incubator Fund 2025