Ethan's head

Ethan Manilow


I am currently a Senior Research Scientist at Google DeepMind on the Magenta Team. I finished my PhD in Computer Science working under Bryan Pardo in the Interactive Audio Lab at Northwestern University. During my PhD, I spent two years as a Student Researcher with Magenta and prior to that, I spent a year and half as Student Researcher at MERL on the Speech and Audio Team. My research centers on making machine learning systems that listen to and understand musical audio in an effort to make tools that can better assist artists.

I live in Chicago, where I spend my free time fingerpicking my acoustic guitar and smiling at dogs I pass on the sidewalk. You can email me at ethan manilow [at] gmail [dot] com.


News

Nov 2024
Promoted to Senior Research Scientist at Google DeepMind!
Oct 2024
New GDM blogpost covering my ongoing GenAI music projects.
Jul 2024
I spoke about Creativity & AI at the Flow Festival in Helsinki.
Apr 2024
I delivered a keynote speech at the XAI Workshop at ICASSP 2024.
Jun 2023
I was recognized as an Outstanding Reviewer at ICASSP 2023.
May 2023
I helped Dan Deacon use AI music tools for his Google I/O Pre-show.
Jan 2023
SingSong paper is now on arXiv.
Aug 2022
I joined Google Brain (now DeepMind) as a Research Scientist.
Jul 2022
I successfully defended my PhD! 👨‍🎓 Read my dissertation here.
May 2022
I will be presenting two papers to ICASSP '22.
Apr 2022
One Oral (MIDI-DDSP) and one Spotlight (MT3) at ICLR '22!
Mar 2022
I am speaking at the London Audio & Music AI Meetup.
Mar 2022
Dec 2021
MIDI-DDSP wins Outstanding Paper at NeurIPS CtrlGen Workshop!
Nov 2021
Hierarchical Instrument Recognition wins Best Paper at ISMIR 2021!
Nov 2021
I will be conducting a tutorial at ISMIR 2021!
Nov 2021
Two papers (1, 2) published at ISMIR 2021!