ABSTRACT
Technology-mediated music performance has long explored the potential of motion interfaces for enhancing musical expression. However designing expressive interactions based on these interfaces and the performer’s skills remains a difficult task because it involves complex and multifaceted motion variability.
In my talk, I will present the various facets of motion variability in music performance and propose a computational approach based on probabilistic modelling and human-centred machine learning. I will present proofs of concept developed and evaluated in the lab, as well as show real world artistic applications and implementation in consumer device product. Finally, I will introduce a more theoretical perspective explored in my current research project at McGill University, funded by the European Commission under the Marie Sklodowska-Curie actions, examining computations underlying sensorimotor learning in music performance, and its impact to enhanced motion interaction.
ABOUT BAPTISTE CARAMIAUX
Baptiste Caramiaux is a Marie Sklodowska-Curie Research Fellow between McGill University (Montreal, Canada) and IRCAM (Paris, France). His current research focuses on the understanding of the cognitive processes of motor learning in musical performance and the computational modelling of these processes. He has worked on gesture expressivity and the design of musical interactive systems through machine learning at IRCAM and Goldsmiths University of London, and applied part of his academic research works on industrial products at Mogees. Baptiste holds a PhD in computer science from University Pierre et Marie Curie in Paris, and IRCAM Centre Pompidou.