Evaluating Human-AI Interaction via Usability, User Experience and Acceptance Measures for MMM-C: A Creative AI System for Music Composition

TL;DR

This study evaluates MMM-Cubase (MMM-C), a 1-parameter co-creative AI interface for music composition, using a mixed-method design with expert hobbyist and professional composers. It integrates MMM into Cubase, assessing usability, user experience, and acceptance via surveys and qualitative coding, supplemented by in-software usage logs. Findings show generally positive usability and acceptance but limited controllability and predictability, indicating that a single parameter is insufficient for expert-level co-creation across genres. The work highlights the importance of exposing additional MMM controls to enhance autonomy, authorship, and creative guidance, and proposes future work to broaden interface capabilities and compare across user groups. The methodological assembly provides a blueprint for evaluating interactive CAC systems in professional music workflows.

Abstract

With the rise of artificial intelligence (AI), there has been increasing interest in human-AI co-creation in a variety of artistic domains including music as AI-driven systems are frequently able to generate human-competitive artifacts. Now, the implications of such systems for musical practice are being investigated. We report on a thorough evaluation of the user adoption of the Multi-Track Music Machine (MMM) as a co-creative AI tool for music composers. To do this, we integrate MMM into Cubase, a popular Digital Audio Workstation (DAW) by Steinberg, by producing a "1-parameter" plugin interface named MMM-Cubase (MMM-C), which enables human-AI co-composition. We contribute a methodological assemblage as a 3-part mixed method study measuring usability, user experience and technology acceptance of the system across two groups of expert-level composers: hobbyists and professionals. Results show positive usability and acceptance scores. Users report experiences of novelty, surprise and ease of use from using the system, and limitations on controllability and predictability of the interface when generating music. Findings indicate no significant difference between the two user groups.

Figures (6)

• Figure 1: MMM-Cubase's Interface in Cubase
• Figure 2: MMM-C Interaction Study Plan & Process
• Figure 3: Task-based SUS Results + Task-based and Overall User-Friendliness Scores
• Figure 4: MMM-Cubase's Controllability Scores
• Figure 5: CSI Factor Scores per Participant Group