Problem
Research questions and friction points this paper is trying to address.
Explainable AI
Material Agency
Neural Audio Models
Musical Interface Design
Human-Computer Interaction
Explainable AI through the Lens of Material Agency: Enabling Musical Interface Design with Neural Audio Models
🤖 AI Summary
This study explores how to enhance the interpretability and manipulability of neural audio models for artists and designers to support their ongoing practice in New Interfaces for Musical Expression (NIME) creation. Treating AI models as “creative materials” with distinct computational properties, the work introduces the concept of “material interpretability” and leverages human–computer interaction methodologies, community-driven co-design, and resource repository development to reframe explainable AI as a supportive toolkit for artistic practice. The contributions include an open-access collection of resources enabling artists to explore neural audio models, multiple NIME prototypes, and three practical principles for fostering inclusive engagement with AI as a creative material—emphasizing its malleability and playfulness.
📝 Abstract
Recent work in Human-Computer Interaction (HCI) increasingly treats AI models as design materials that have distinctive computational properties to shape design artifacts. Artists learn to work with the model "at play" to explore their emerging properties. The aim of explainability, in this view, is to make visible a crafting and hacking space to enable sustained creative practices with AI. In this chapter, we propose material explainability as a range of activities and artifacts that transform AI models into accessible and inclusive design materials in the workspace of artists, designers, and makers. We present a case study of building a repository of resources to enable artistic explorations of neural audio models in New Interfaces for Musical Expression (NIME) design. Reflecting on our community-building journey and the making of a collection of musical interface designs with a group of artists, we raise three recommendations on enabling the exploration of AI as materials in artistic practices to inspire future XAI design for artists.
Innovation
Methods, ideas, or system contributions that make the work stand out.
material explainability
neural audio models
Human-Computer Interaction
design materials
New Interfaces for Musical Expression
🔎 Similar Papers
No similar papers found.
