Machine Learning for Musicians and Artists

Dr. Rebecca Fiebrink is a Lecturer in Computing at Goldsmiths, University of London. She creates new technologies for digital music and art, and she designs new ways for humans to interact with computers in creative practice. Much of her current research combines techniques from human-computer interaction, machine learning, and signal processing to allow people to apply machine learning more effectively to new problems, such as the design of new digital musical instruments and gestural interfaces for gaming and health. She is also involved in projects developing rich interactive technologies for digital humanities scholarship, and in designing new approaches to integrating the arts into computer science teaching and outreach.

Rebecca is the developer of the Wekinator system for interactive machine learning. She has worked with companies including Microsoft Research, Sun Microsystems Research Labs, Imagine Research (recently acquired by iZotope), and Smule, where she helped to build the #1 iTunes app “I am T-Pain.” An active musician, she has performed regularly with a variety of musical ensembles, including as a laptopist in Sideband, the principal flutist in the Timmins Symphony Orchestra, and the keyboardist in the University of Washington computer science rock band “The Parody Bits.” Prior to arriving at Goldsmiths, she held a faculty position at Princeton University.

Laetitia Sonami is a sound artist and performer. Her sound performances, live-film collaborations and sound installations explore ideas of presence and participation.

Sonami’s work combines text, music and “found sound” from the world, in compositions which have been described as “performance novels. Her signature instrument, the Lady’s Glove, is fitted with a vast array of sensors which track the slightest motion of her enigmatic dance: with it Sonami can create performances where her movements can shape the music and in some instances visual environments. The lady’s glove has become a fine instrument which challenges notions of technology and virtuosity.Composer, performer, and sound installation artist Laetitia Sonami was born in France and settled in the United States in 1975 to pursue her interest in the emerging field of electronic music. She studied with Eliane Radigue, Joel Chadabe, Robert Ashley and David Behrman.

Sonami lives in Oakland, California and is guest lecturer at the San Francisco Art Institute and the Milton Avery MFA program at Bard College.

Baptiste Caramiaux is a post-doctoral researcher in the Embodied Audio-Visual Interaction group at Goldsmiths, University of London. Prior to Goldsmiths, he completed his PhD at Ircam Centre Pompidou in Paris, in the Sound Music Movement Interaction group. Baptiste's work focuses on Human Motion in Interactive Systems, in particular for creative applications with Music. His research involves Cognition (link between motor and auditory systems), Bayesian Machine Learning and Interaction Design (interaction techniques, interaction models). Baptiste is interested in new forms of expression based on human motion in interactive contexts, involving sound or visual manipulation in creative applications. His approach is based on Machine Learning techniques and Bayesian inference of the expressive information from motion capture data (3-d systems, physiological data, inertial data, etc.). The methods developed are specifically designed to be used in creative applications, involving exploration and improvisation, such as Music. In parallel, he is also interested in the perception side of the interaction with digital media. Part of this research is to conduct controlled experiments in order to investigate how our gesture can describe how we perceive sounds (a form of embodied sound cognition).