TitleMachine Improvisation with Formal Specifications
Publication TypeConference Paper
Year of Publication2014
AuthorsDonze, A, Akkaya, I, Seshia, SA, Libkind, S, Valle, R, Wessel, D
Conference NameInternational Computer Music Conference
Date Published14/09/2014
Conference LocationAthens, Greece

We define the problem of machine improvisation of music with formal specifications. In this problem, one seeks to create a random improvisation of a given reference melody that however satisfies a specification encoding constraints that the generated melody must satisfy. More specifically, we consider the scenario of generating a monophonic Jazz melody (solo) on a given song harmonization. The music is encoded symbolically, with the improviser generating a sequence of note symbols comprising pairs of pitches (frequencies) and discrete durations. Our approach can be de- composed roughly into two phases: a generalization phase, that learns from a training sequence (e.g., obtained from a human improviser) an automaton generating similar sequences, and a supervision phase that enforces a specification on the generated sequence, imposing constraints on the music in both the pitch and rhythmic domains. The supervision uses a measure adapted from Normalized Compression Distances (NCD) to estimate the divergence be- tween generated melodies and the training melody and em- ploys strategies to bound this divergence. An empirical evaluation is presented on a sample set of Jazz music.