Machine Learning for Musical Expression: Analysis of the practices and culture of machine learning in NIME community

People involved

Théo Jourdan
Baptiste Caramiaux

Abstract

New Interfaces for Musical Expression (NIME) community gathers researchers and musicians from all over the world to share their knowledge and late-breaking work on new musical interface design. They have been involved in the development of Machine Learning (ML) and its use in a creative context from an early stage. For several decades NIME community has always been appropriating ML to apply for various tasks such as gesture-sound mapping or sound synthesis for digital musical instruments. Recently, the use of ML methods seems to have increased and the objectives have diversified. Despite its increasing use, few contributions have studied what constitutes the culture of learning technologies for this specific practice.
This project aims at analyzing in a first time, the practices involving ML in terms of the techniques and the task used and the ways to interact this technology through systematic review. In a second time, we analyzed the cultural and political sides of these practices. In order to explore how practitioners in the NIME community engage with ML techniques through semi-structured interviews and thematic analysis.
It thus contributes to a deeper understanding of the specific goals and motivation in using ML for musical expression.

Systematic review paper: https://hal.science/hal-04075492
Interviews paper: https://hal.science/hal-04075438