I am a PhD researcher at the RITMO Centre for Interdisciplinary Studies of Rhythm, Time and Motion at the University of Oslo.
With a background in music production and an MSc. in Informatics, my academic interests lie in the cross-section between art and science.
My current research is centered around sound-motion mappings with 3D motion capture, generative machine learning and the use of AI as a tool for pursuing and understanding creativity.
The inherently subjective notion of quality in creative artifacts centers both technical and philosophical questions regarding AI-generated art. In this thesis the development and evaluation of AI-generated dance forms the context within which these questions are explored.
Dance is a multifaceted art form. In rituals and celebrations, improvised or choreographed, a social glue and personal expression, dance plays a role in all human cultures and many aspects of life. Dance movement is also a rich, complex data source.
The main objectives of this thesis are to understand more about how deep learning can be used to capture salient features of movement, and especially dance movement, using full-body motion capture data. We further explore how such technology might be aimed to benefit the creative practice of dancers.
Vocal looper with Harmony Prediction by BLSTMs (paper)
1-minute thesis
Full-body Motion capture of Improvised dance (dataset)
Soft controllers