AI-Assisted Music Production: A User Study on Text-to-Music Models

2025-09-27

AI Summary

This study addresses the practical integration of text-to-music (TTM) models into professional music production workflows—a domain largely unexamined in prior research, particularly regarding impacts on creators’ practices, agency, and ethical reasoning. Method: We designed and deployed a customized创作 tool integrating TTM generation with source separation, conducting a real-world user study with 12 professional music producers. Data were collected via semi-structured interviews and analyzed using thematic analysis. Contribution/Results: As the first empirical investigation focused specifically on TTM “workflow embedding,” our findings reveal that TTM significantly accelerates creative ideation and broadens sonic experimentation; however, it simultaneously introduces critical challenges concerning generation controllability, authorship attribution, and copyright ownership. These insights provide foundational empirical evidence to inform human-centered AI music tool design and industry-wide policy development.

Technology Category

• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Game Design — Procedural Content Generation & Storytelling

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• User Modeling, Personalization and Recommendation: Accountability, Transparency, and Ethics for personalization
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Text-to-music models have revolutionized the creative landscape, offering new possibilities for music creation. Yet their integration into musicians workflows remains underexplored. This paper presents a case study on how TTM models impact music production, based on a user study of their effect on producers creative workflows. Participants produce tracks using a custom tool combining TTM and source separation models. Semi-structured interviews and thematic analysis reveal key challenges, opportunities, and ethical considerations. The findings offer insights into the transformative potential of TTMs in music production, as well as challenges in their real-world integration.

Problem

• Investigating text-to-music models' integration into musician workflows
• Evaluating AI tools' impact on creative processes and challenges
• Exploring ethical considerations in real-world music production applications

Innovation

• Combining text-to-music and source separation models
• Developing custom tool for music production workflows
• Using semi-structured interviews and thematic analysis