Interaction with machine improvisation

Gerard Assayag, George Bloch, Arshia Cont, Shlomo Dubnov

Research output: Chapter in Book/Report/Conference proceedingChapterpeer-review

6 Scopus citations

Abstract

We describe two multi-agent architectures for an improvisation oriented musician-machine interaction systems that learn in real time from human performers. The improvisation kernel is based on sequence modeling and statistical learning. We present two frameworks of interaction with this kernel. In the first, the stylistic interaction is guided by a human operator in front of an interactive computer environment. In the second framework, the stylistic interaction is delegated to machine intelligence and therefore, knowledge propagation and decision are taken care of by the computer alone. The first framework involves a hybrid architecture using two popular composition/ performance environments, Max and OpenMusic, that are put to work and communicate together, each one handling the process at a different time/memory scale. The second framework shares the same representational schemes with the first but uses an Active Learning architecture based on collaborative, competitive and memory-based learning to handle stylistic interactions. Both systems are capable of processing real-time audio/video as well as MIDI. After discussing the general cognitive background of improvisation practices, the statistical modelling tools and the concurrent agent architecture are presented. Then, an Active Learning scheme is described and considered in terms of using different improvisation regimes for improvisation planning. Finally, we provide more details about the different system implementations and describe several performances with the system.

Original languageEnglish
Title of host publicationThe Structure of Style
Subtitle of host publicationAlgorithmic Approaches to Understanding Manner and Meaning
PublisherSpringer Berlin Heidelberg
Pages219-245
Number of pages27
ISBN (Print)9783642123368
DOIs
StatePublished - 1 Dec 2010
Externally publishedYes

ASJC Scopus subject areas

  • Computer Science (all)

Fingerprint

Dive into the research topics of 'Interaction with machine improvisation'. Together they form a unique fingerprint.

Cite this