Title: Virtual muscians and live jazz performance
I am leading the music research team at SONY Computer Science Laboratory Paris, where I developed the vision that metadata can greatly enhance the musical experience in all its dimensions, from listening to performance. I carried on research on interactive music listening and performance and musical metadata, and developed several innovative technologies (constraint-based spatialization, intelligent music scheduling using metadata) and award winning systems (MusicSpace, PathBuilder, The Continuator for Interactive Music Improvisation, etc.) My recent goal is to create a new generation of authoring tools able to boost individual creativity. These tools, called Flow Machines, help us create original content through "reflexive interaction" or dialogues with oneself. Flow machines abstract "style" from concrete corpora (text, music, etc.), and turn it into a malleable substance that acts as a texture. Applications range from music composition to text or drawing generation and probably much more. Technically, these systems raise issues in machine-learning (learning style, extracting features), combinatorial optimization (fitting styles to arbitrary constraints) and knowledge representation. Current projects are Miror (reflexive interactions for teaching music to children) and Flow Machines, a large-scale project sponsored by an ERC Advanced Grant.