Case-based Melody Generation with MuzaCazUza



MuzaCazUza is a system for interactive composition of musical ideas in two phases: first, the program composes a melody by the application of Case-based Reasoning (CBR) techniques, according to a given harmonic line and a set of pre-defined structure; then, a set of transformation operators are available to change the generated idea.
We believe analogy-based architectures (like CBR) are a fertile ground to model computational creativity and, more specifically, musical composition. Indeed, our everyday reasoning, be it more or less creative, has the constant presence of past experience and it is not uncommon in the Music field to notice recurrence of themes, rhythmic patterns, melodic cells, and other musical objects from previous compositions.
In this paper, we describe MuzaCazUza in some detail and discuss some practical and theoretical issues that will appear within context. We also show some preliminary results.


AI and Music


AISB'01, March 2001

PDF File

Cited by

Year 2013 : 1 citations

 Fernández, J. D., & Vico, F. (2013). AI Methods in Algorithmic Composition: A Comprehensive Survey. Journal of Artificial Intelligence Research, 48, 513-582.

Year 2007 : 1 citations

 Endbericht zum Projekt Virtual Gamelan Graz (VGG). Gerhard Eckel, Gerd Grupe, Robert Höldrich, Gerhard Nierhaus, Rainer Schu?tz, Alois Sontacchi and Franz Zotter. IEM reports. Publications of Institut für Elektronische Musik und Akustik. 2007

Year 2001 : 1 citations

 Colton, S., Pease, A. and Ritchie, G. "The Effect of Input Knowledge on Creativity". Proceedings of the ICCBR'01 Workshop on Creative Systems, Vancouver, Canada, 2001