Revival: Collaborative Artistic Creation through Human-AI Interactions in Musical Creativity
Keon Ju M. Lee, Philippe Pasquier, Jun Yuri
TL;DR
Revival investigates live improvisation that merges human performance with AI musical agents trained on deceased composers. It deploys MASOM, SpireMuse, and MACAT within a conductor-enabled, audio-reactive visual pipeline using Autolume and a human-guided VJ, highlighting a small data approach and ethical considerations. The work articulates a research-creation methodology to study co-creation, authorship, and audience perception in AI-enhanced music and visuals. It demonstrates practical integration of cross-modal systems and outlines challenges and future directions for scalable human-AI collaboration in the arts.
Abstract
Revival is an innovative live audiovisual performance and music improvisation by our artist collective K-Phi-A, blending human and AI musicianship to create electronic music with audio-reactive visuals. The performance features real-time co-creative improvisation between a percussionist, an electronic music artist, and AI musical agents. Trained in works by deceased composers and the collective's compositions, these agents dynamically respond to human input and emulate complex musical styles. An AI-driven visual synthesizer, guided by a human VJ, produces visuals that evolve with the musical landscape. Revival showcases the potential of AI and human collaboration in improvisational artistic creation.