Learning Models for Interactive Melodic Improvisation
Belinda Thom · 1999
. This research addresses the problem of the computer interacting with a live, improvising musician in the jazz/blues setting. We introduce BoB, a model of improvisation that enables the computer to trade solos with a musician in an adaptive, user-specific manner. We develop unsupervised learning methods for autonomously customizing the model via improvised examples and demonstrate the powerful musical abstractions that emerge when applied to Charlie Parker's Mohawk improvisations. Our key technical contribution is the development of an architecture that naturally enables unsupervised learned knowledge, perception and generation to be tightly coupled. 1 Introduction This research addresses the problem of the computer interacting with a live, improvising musician in the jazz/blues setting. The long-term research goal is to create computer music algorithms and tools that enhance the organic, adaptive, melodic evolution that takes place when a soloing improviser practices alone with a...