Saved in:
Bibliographic Details
Main Authors: Lee, Keon Ju M., Pasquier, Philippe
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2502.00023
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909471773556736
author Lee, Keon Ju M.
Pasquier, Philippe
author_facet Lee, Keon Ju M.
Pasquier, Philippe
contents Our research explores the development and application of musical agents, human-in-the-loop generative AI systems designed to support music performance and improvisation within co-creative spaces. We introduce MACAT and MACataRT, two distinct musical agent systems crafted to enhance interactive music-making between human musicians and AI. MACAT is optimized for agent-led performance, employing real-time synthesis and self-listening to shape its output autonomously, while MACataRT provides a flexible environment for collaborative improvisation through audio mosaicing and sequence-based learning. Both systems emphasize training on personalized, small datasets, fostering ethical and transparent AI engagement that respects artistic integrity. This research highlights how interactive, artist-centred generative AI can expand creative possibilities, empowering musicians to explore new forms of artistic expression in real-time, performance-driven and music improvisation contexts.
format Preprint
id arxiv_https___arxiv_org_abs_2502_00023
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Musical Agent Systems: MACAT and MACataRT
Lee, Keon Ju M.
Pasquier, Philippe
Multiagent Systems
Artificial Intelligence
Human-Computer Interaction
Sound
Audio and Speech Processing
Our research explores the development and application of musical agents, human-in-the-loop generative AI systems designed to support music performance and improvisation within co-creative spaces. We introduce MACAT and MACataRT, two distinct musical agent systems crafted to enhance interactive music-making between human musicians and AI. MACAT is optimized for agent-led performance, employing real-time synthesis and self-listening to shape its output autonomously, while MACataRT provides a flexible environment for collaborative improvisation through audio mosaicing and sequence-based learning. Both systems emphasize training on personalized, small datasets, fostering ethical and transparent AI engagement that respects artistic integrity. This research highlights how interactive, artist-centred generative AI can expand creative possibilities, empowering musicians to explore new forms of artistic expression in real-time, performance-driven and music improvisation contexts.
title Musical Agent Systems: MACAT and MACataRT
topic Multiagent Systems
Artificial Intelligence
Human-Computer Interaction
Sound
Audio and Speech Processing
url https://arxiv.org/abs/2502.00023