Machine Learning of Musical Gestures

Caramiaux, Baptiste and Tanaka, Atau

Proceedings of the International Conference on New Interfaces for Musical Expression

We present an overview of machine learning (ML) techniques and theirapplication in interactive music and new digital instruments design. We firstgive to the non-specialist reader an introduction to two ML tasks,classification and regression, that are particularly relevant for gesturalinteraction. We then present a review of the literature in current NIMEresearch that uses ML in musical gesture analysis and gestural sound control.We describe the ways in which machine learning is useful for creatingexpressive musical interaction, and in turn why live music performance presentsa pertinent and challenging use case for machine learning.