Hello!

Annie Chu

I'm Annie (she/her), a 4th year PhD student at Northwestern University in the Technology & Social Behavior program, a dual PhD program in Computer Science and Communications.

I'm currently at the Interactive Audio Lab, advised by Dr. Bryan Pardo. My research interests lie at the intersection of audio, deep learning, human-computer interaction, and computational musicology.

Previously, I completed my B.S. in Electrical & Computer Engineering with a concentration in Media Arts at Olin College of Engineering. In my free time, you can find me walking around record shops, watching stand up, or playing bananagrams. As a native New Yorker (Queens!!!), I am also on the hunt for the best bagel in Chicago. Please email me if you find it.

You can reach me at anniechu [at] u.northwestern.edu

Updates

papers
general
Sep 2026
I wrote a book review of Seth Long’s The Last Mixtape: Physical Media and Nostalgic Cycles for the IASPM Journal.
Aug 2026
Taught CS352: Machine Perception of Music & Audio as Instructor of Record (Summer 2026)
July 2026
Our work Smorph: Playable Sound Morphing with Diffusion Models was accepted to ISMIR 2026!
July 2026
D-Composer: Language Modeling for Simultaneous Drum Transcription and Sound Event Decomposition, work led by Patrick O'Reilly was accepted to ISMIR 2026! Check out the demo page.
July 2026
Presented our work-in-progress paper, SLIME: Streaming Listener Index of Musical Experience at SMPC 2026
April 2026
Our work FXplorer was accepted to NIME 2026! Learn more here.
March 2026
Presented Listening in the Age of the Algorithm: Bridging Musicology and HCI Methodologies at Clouds, Streams, and Ground (Truths) Conference 2026 in Berkeley, CA.
Jan 2026
Our work Mix2Morph: Learning Sound Morphing from Noisy Mixes was accepted at ICASSP 2026 (to be presented May 2026 in Barcelona!). See demo page.
Summer 2025
Interned at Adobe SODA (Sound Design AI group)
July 2025
Sound Check: Auditing Recent Audio Dataset Practices, work led by William Agnew was accepted into AIES 2025. Check out the paper.
June 2025
The Rhythm In Anything (TRIA): Audio-prompted Drums generation with masked language modeling, work led by Patrick O'Reilly, was accepted at ISMIR 2025. Check out the demo page.
April 2025
Presented our work Text2FX at ICASSP 2025! Check out the paper (arXiv) and the demo page.