Learning Models for Interactive Melodic Improvisation
نویسنده
چکیده
Belinda Thom School of Computer Science Carnegie Mellon University Pittsburgh, PA 15213, U.S.A. Abstract. 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-speci c 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.
منابع مشابه
Learning and the Evolution of Melodic Complexity in Virtuoso Jazz Improvisation
Spontaneous musical improvisation in jazz depends upon a substantial cognitive scaffolding that enables the real-time generation of creative structures. This work describes a computational model that simulates sub-conscious learning processes through an evolutionary paradigm.
متن کاملUnsupervised Learning and Interactive Jazz/Blues Improvisation
We present a new domain for unsupervised learning: automatically customizing the computer to a specific melodic performer by merely listening to them improvise. We also describe BoB, a system that trades customized real-time solos with a specific musician. We develop a probabilistic mixture model, derived from the multinomial distribution, for the clustering and generation of variable sample-si...
متن کاملAutomatic Classification of Guitar Playing Modes
Musicians typically use various playing modes (bass lines, chord comping, solo melody improvisation) when they perform with their instrument. The design of augmented instruments calls for a precise understanding of such playing modes, from real-time analysis of musical input. In this context, the accuracy of mode classification is critical because it underlies the design of the whole interactio...
متن کاملLearning to Create Jazz Melodies Using Deep Belief Nets
We describe an unsupervised learning technique to facilitate automated creation of jazz melodic improvisation over chord sequences. Specifically we demonstrate training an artificial improvisation algorithm based on unsupervised learning using deep belief nets, a form of probabilistic neural network based on restricted Boltzmann machines. We present a musical encoding scheme and specifics of a ...
متن کاملAssistive Technology and Performance Behaviours in Music Improvisation
The findings from three trial workshops with a group of music-learners with physical disabilities have culminated in an initial design for a novel interactive music-generation system. Using a variety of commercially available musictechnologies in a synchronised set-up, the target group identified those aspects of both music production and accessible interaction that were most appealing and prod...
متن کامل