Machine Learning for Musical Expression: A Systematic Literature Review
Théo Jourdan, Baptiste Caramiaux
Abstract
For several decades NIME community has always been appropriating machine learning (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 paper presents an analysis of 69 contributions selected from a systematic review of the NIME conference over the last 10 years. This paper aims at analysing the practices involving ML in terms of the techniques and the task used and the ways to interact this technology. It thus contributes to a deeper understanding of the specific goals and motivation in using ML for musical expression. This study allows us to propose new perspectives in the practice of these techniques.