Novice-AI Music Co-Creation via AI-Steering Tools for Deep Generative Models


While generative deep neural networks (DNNs) have demonstrated their capacity for creating novel musical compositions, less attention has been paid to the challenges and potential of co-creating with these musical AIs, especially for novices. In a needfinding study with a widely used, interactive musical AI, we found that the AI can overwhelm users with the amount of musical content it generates, and frustrate them with its non-deterministic output. To better match co-creation needs, we developed AI-steering tools, consisting of Voice Lanes that restrict content generation to particular voices; Example-Based Sliders to control the similarity of generated content to an existing example; Semantic Sliders to nudge music generation in high-level directions (happy/sad, conventional/surprising); and Multiple Alternatives of generated content to audition and choose from. In a summative study (N=21), we discovered the tools not only increased users' trust, control, comprehension, and sense of collaboration with the AI, but also contributed to a greater sense of self-efficacy and ownership of the composition relative to the AI.

Human-AI Interaction
Generative Deep Neural Networks
Ryan Louie
Northwestern University, Evanston, IL, USA
Andy Coenen
Google Research, Mountain View, CA, USA
Cheng Zhi Huang
Independent Researcher, Mountain View, CA, USA
Michael Terry
Google Research, Cambridge, MA, USA
Carrie J. Cai
Google Research, Mountain View, CA, USA




会議: CHI 2020

The ACM CHI Conference on Human Factors in Computing Systems (

セッション: Music & sound experiences

Paper session
5 件の発表
2020-04-29 01:00:00
2020-04-29 02:15:00