Patrick O'Reilly

Contact · Google Scholar · Twitter · Music · CV

I am a doctoral student in the Department of Computer Science at Northwestern University and a member of the Interactive Audio Lab. I received a BA in Mathematics and Music from Carleton College and an MS in Computer Science from the University of Illinois at Chicago. My research interests include content provenance for generative models, machine learning techniques for controllable audio generation, and music information retrieval.

News

9.23.2025 I presented our work The Rhythm In Anything at ISMIR 2025 in Daejeon

8.17.2025 I gave a tutorial on speech watermarking at ISCA Interspeech 2025 in Rotterdam; slides and code are available here

4.27.2025 Our work Deep Audio Watermarks are Shallow was presented at the first ICLR Workshop on Gen AI Watermarking

4.10.2025 I presented our work Code Drift at ICASSP 2025 in Hyderabad

2.2.2025 I passed my PhD prospectus and plan to defend my dissertation in 2026

Research Playlist

The Rhythm In Anything: Audio-Prompted Drums Generation with Masked Language Modeling

Patrick O’Reilly, Julia Barnett, Hugo Flores García, Annie Chu, Nathan Pruyne, Prem Seetharaman, Bryan Pardo

Paper (ISMIR 2025) · Abstract (ISMIR 2024 Late-Breaking Demo) · Project Page · Code · Copy BibTeX

Deep Audio Watermarks are Shallow: Limitations of Post-Hoc Watermarking Techniques for Speech

Patrick O’Reilly, Zeyu Jin, Jiaqi Su, Bryan Pardo

Paper (ICLR 2025 Workshop on GenAI Watermarking) · Project Page · Copy BibTeX

Code Drift: Towards Idempotent Neural Audio Codecs

Patrick O’Reilly, Prem Seetharaman, Jiaqi Su, Zeyu Jin, Bryan Pardo

Paper (ICASSP 2025) · Project Page · Copy BibTeX

Text2FX: Harnessing CLAP Embeddings for Text-Guided Audio Effects

Annie Chu, Patrick O’Reilly, Julia Barnett, Bryan Pardo

Paper (ICASSP 2025) · Project Page · Copy BibTeX

MaskMark: Robust Neural Watermarking for Real and Synthetic Speech

Patrick O’Reilly, Zeyu Jin, Jiaqi Su, Bryan Pardo

Paper (ICASSP 2024) · Project Page · Copy BibTeX

HARP: Bringing Deep Learning to the DAW with Hosted, Asynchronous, Remote Processing

Hugo Flores García, Christodoulos Benetatos, Patrick O’Reilly, Aldo Aguilar, Zhiyao Duan, Bryan Pardo

Paper (NeurIPS 2023 MLCD Workshop) · Project Page · Code · Copy BibTeX

VoiceBlock: Privacy through Real-Time Adversarial Attacks with Audio-to-Audio Models

Patrick O'Reilly, Andreas Bugler, Keshav Bhandari, Max Morrison, Bryan Pardo

Paper (NeurIPS 2022) · Project Page · Video · Code · Copy BibTeX

Effective and Inconspicuous Over-the-Air Adversarial Examples with Adaptive Filtering

Patrick O'Reilly, Pranjal Awasthi, Aravindan Vijayaraghavan, Bryan Pardo

Paper (ICASSP 2022) · Project Page · Talk @ BishBash · Code · Copy BibTeX

Unsupervised Source Separation By Steering Pretrained Music Models

Ethan Manilow, Patrick O'Reilly, Prem Seetharaman, Bryan Pardo

Paper (ICASSP 2022) · Project Page · Code · Copy BibTeX

Audio summaries generated by Google NotebookLM

0:00