Seminar: Generating music in the raw audio domain

SpeakerSander Dieleman
DateFriday, 01 Mar 2019
Time13:00 - 14:00
LocationRoberts 421
Event seriesDeepMind CSML Seminar Series

Realistic music generation is a challenging task. When machine learning is used to build generative models of music, typically high-level representations such as scores, piano rolls or MIDI sequences are used that abstract away the idiosyncrasies of a particular performance. But these nuances are very important for our perception of musicality and realism, so we embark on modelling music in the raw audio domain. I will discuss some of the advantages and disadvantages of this approach, and the challenges it entails.

iCalendar csml_id_372.ics