Creating music at Jukedeck

By Katerina Kosta (Jukedeck)

Abstract:

This presentation starts with an introduction about Jukedeck, an Artificial Intelligence music generation system, its products and aims. Then it focuses on the challenges a music AI system faces in order to create plausible music excerpts; from gathering and cleaning data, learning musical structure, and evaluating the outcome to synthesising audio.    

Bio:

Katerina is a machine learning researcher at Jukedeck, working as part of the composition team, whose aim is to develop machine learning systems for music generation. She pursued her PhD at the Centre for Digital Music, Queen Mary University of London, conducting research on modelling dynamic variations in expressive music performance. She received degrees from University of Athens (Mathematics) and Filippos Nakas Conservatory, Athens (Piano), and a Sound and Music Computing Masters from the Music Technology Group, UPF, Barcelona.