The Isomer Project is an effort to manifest the goal of computational creativity in the realm of automated music creation. Isomer analyzes human-created music by reading scores and listening to recordings, and among other things, composes new music based on what it learns.
Musical language is abstract in the sense that it doesn’t contain lexical morphemes — units of grammar that carry with them specific meaning(s). This freedom from restrictive definitions is arguably one of music’s most compelling features, but it also makes parsing its largely self-referential and often emergent grammar extremely challenging.
Bridging the gap between raw features and musically meaningful analysis is essential to computational creativity, and is a primary force behind the design and architecture of the Isomer codebase. Although it’s a work in progress, Isomer is already creating its own music — you can hear examples here. Isomer has also been used in research to help uncover how musical features connect with the emotions we feel.