Musical Agent Systems: MACAT and MACataRT
This work addresses the need for ethical and transparent AI tools in music performance and improvisation, though it appears incremental as it builds on existing generative AI concepts for co-creative spaces.
The research tackled the problem of enhancing interactive music-making between human musicians and AI by developing MACAT and MACataRT, two musical agent systems that support performance and improvisation through real-time synthesis and audio mosaicing, resulting in expanded creative possibilities for musicians.
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.