An Expert System for Computer-Assisted Composition
David Cope · Computer Music Journal · 1987
Computers offer opportunities for style imitation (Hiller and Isaacson 1959; Winograd 1968; Lidov and Gabura 1973) and afford novel solutions to problems in music composition. They have been successfully used in automated music (Hiller and Isaacson 1959), algorithmic composition (Fry 1984), and as stochastic probability generators (Xenakis 1971), to name a few. Artificial systems have created serious interest for music analysis (Roads 1985a) and composition (Cope 1987). Experiments in music intelligence (EMI) was begun (1984) as an interactive partner for the author. Initially viewed as an analysis tool for generating extensive lists of motivic patterns, it quickly grew into an imitative projector of possible next intervals of given phrases. From these early programs grew a large set of functions that allowed for style dictionaries and syntax rule applications. Rather than avoiding the author's own biases, the system developed explicitly around them. These included projections of linguistic parselike networks for phrase structures, intensely rigorous motive replications, and a proclivity for analyzing music by intervals rather than by pitch.