Functional Scaffolding for Musical Composition (FSMC)

Functional Scaffolding for Musical Composition (FSMC) is a method automated music generation that focuses on accompaniment and harmonization. It is based on the idea that music can be represented as a pattern that is a function of time, i.e. f(t). Thus the temporal patterns of different parts in a piece are functionally related to each other. Building on this idea, FSMC searches for transforming functions that transform an existing part of a composition, called the scaffold, into a new part, which is the generated accompaniment. Thus rather than searching for sequences of notes FSMC searches for functions that transform scaffolds, thereby inheriting the structure and nuances of the scaffold automatically. Drum patterns and harmonies are evolved through Interactive Evolutionary Computation (IEC), wherein the user breeds muisical pieces by selecting those that are most appealing. Publications describing this approach, links to a program that implements the technology, MaestroGenesis, and corresponding musical samples generated for each paper are given below:

To download MaestroGenesis that is based on FSMC, click here


Generating Musical Accompaniment with Functional Scaffolding
Amy K. Hoover, Paul A. Szerlip, and Kenneth O. Stanley
Department of Electrical Engineering and Computer Science, University of Central Florida
To appear in: Proceedings of the 8th Sound and Music Computing Conference (SMC-2011, Padova, Italy).
Music Samples for SMC 2011

Interactively Evolving Harmonies with Functional Scaffolding
Amy K. Hoover, Paul A. Szerlip, and Kenneth O. Stanley
Department of Electrical Engineering and Computer Science, University of Central Florida
To appear in: Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2011). New York, NY:ACM (8 pages)
Winner of the Best Paper Award at GECCO 2011
Music Samples for GECCO 2011

Exploiting Functional Relationships in Musical Composition
Amy K. Hoover and Kenneth O. Stanley
School of Electrical Engineering and Computer Science, University of Central Florida
Connection Science Special Issue on Music, Brain, & Cognition. Abington, UK: Taylor & Francis, 2009. Manuscript 33 pages
Music Samples for Connection Science 2009

Scaffolding for Interactively Evolving Novel Drum Tracks for Existing Songs
Amy K. Hoover, Michael P. Rosario, and Kenneth O. Stanley
School of Electrical Engineering and Computer Science, University of Central Florida
In: Proceedings of the Sixth European Workshop on Evolutionary and Biologically Inspired Music, Sound, Art and Design (EvoMUSART 2008). New York, NY: Springer, 2008. 10 pages.
Winner of the Best Paper Award at EvoMUSART 2008
Music Samples for EvoMUSART 2008

Credits:

Implementation and Design:
    Amy K. Hoover and Paul A. Szerlip
Project Supervisor:
    Kenneth O. Stanley
Testing:
    Trevor Brindle, Zack Merritt, and Marie Norton
© 2011 Evolutionary Complexity Research Group at the University of Central Florida