People

Bryan Pardo

Professor

I head the Interactive Audio Lab.

Jason Brent Smith

Postdoctoral Scholar

Jason Smith is a Postdoctoral Scholar at Northwestern University and a member of the Interactive Audio Lab. He received a PhD in Music Technology at the Georgia Institute of Technology. His research interests include Human-AI collaboration, interactive music, and the use of AI to support creativity and accessibility. In his free time, he enjoys playing Jazz Bass.

Hugo Flores Garcia

Doctoral Student

Hugo Flores Garcia is a doctoral student at Northwestern University and a member of the Interactive Audio Lab. His research interests include audio source separation, designing accessible musical interfaces, and algorithmic composition. Hugo enjoys exploring the ways computers can be used to enhance creative expression, as well as playing jazz guitar. [website]

Patrick O'Reilly

Doctoral Student

Patrick O’Reilly is a doctoral student at Northwestern University and a member of the Interactive Audio Lab. He received a BA in Mathematics and Music from Carleton College and an MS in Computer Science from the University of Illinois at Chicago. His research interests include adversarial robustness, music information retrieval, and generative models for audio. In his free time, he enjoys playing guitar and writing music.

Julia Barnett

Doctoral Student

Julia Barnett is a doctoral student at Northwestern University. Her research interests lie in reducing the socio-technical harms of algorithmic systems and deep generative applications in social contexts. She received a MS in Data Science from the Barcelona School of Economics and a BBA from Villanova University. In her free time, she enjoys kayaking and playing music. [website]

Annie Chu

Doctoral Student

Annie Chu is a doctoral student at Northwestern University and a member of the Interactive Audio Lab. Her research interests include accessible & inclusive musical interfaces, audio and machine learning, human-computer interaction, and multimodal systems. She received her BS in Electrical & Computer Engineering from Olin College of Engineering. In her free time, she enjoys exploring Chicago’s record shops, swimming, and playing bananagrams.

Lindsey Qixin Deng

Masters Student

Lindsey is a master’s student in Electrical Engineering at Northwestern University. She holds a BS in Audio and Music Engineering from the University of Rochester. She is currently working on software development for HARP and conducting research on the perceptual grounding of deep audio embeddings. Her research interests include audio signal processing, music information retrieval, and generative models for audio. In her free time, she enjoys learning to DJ, exploring sound design with modular synthesizers, and attending live-house concerts.

Saumya Pailwan

Masters Student

Saumya Pailwan is a Master’s student in Computer Science at Northwestern University and a member of the Interactive Audio Lab. Her research interests include machine learning, audio, and generative models, with current work focused on improving symbolic music generation using discrete diffusion and remasking strategies. In her free time, she enjoys listening to music and exploring how artistic forms can inform new directions in technology.

Adrian Hoffer

Masters Student

Adrian Hoffer is a masters student studying Computer Science at Northwestern University and also a member of the Interactive Audio Lab. He currently works with Patrick on using discrete diffusion for symbolic music generation and continuation tasks. In his free time he listens to lots of Santana and Jamiroquai as well as playing pickup basketball at Northwestern’s courts.

Max Morrison

Research Scientist, Murf.AI

Max defended his thesis in 2024 and is now a research scientist at Murf.ai building AI-enabled speech content creation software for podcasts, film dialogue, educational content, and more. He received his PhD from the Interactive Audio Lab at Northwestern University (advised by Bryan Pardo). His research interests include generative modeling, audio editing, and interpretable representations for interactive applications (e.g., content creation, language learning, or speech pathology). Before beginning doctoral research, he attended the University of Michigan and obtained Bachelor’s degrees in Computer Science and Performing Arts Technology.

Ethan Manilow

Senior Research Scientist, Google Deep Mind

Ethan is currently a Research Scientist at Google DeepMind on the Magenta Team. He finished my PhD in Computer Science in 2022 working under Bryan Pardo in the Interactive Audio Lab at Northwestern University. During his PhD, he spent two years as a Student Researcher with Magenta and prior to that, spent a year and half as Student Researcher at MERL on the Speech and Audio Team. His 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.

Fatemeh Pishdadian

Research Engineer, Apple

Fatemeh defended her dissertation in October 2020 in in the Department of Computer Science. Her research interest lies in the application of signal processing and machine learning techniques to the analysis of audio/music. She is currently a research engineer at Apple.

Bongjun Kim

AI researcher, Solventum

Bongjun is currently an AI researcher at Solventum. He completed his PhD in 2020 in computer science at Northwestern University as a member of the Interactive Audio Lab (Advisor: Bryan Pardo). His research interests inlucde machine learning, audio signal processing (e.g., sound event recognition), intelligent interactive system, multimedia information retrieval, and human-in-the-loop interface. He enjoys working on a musical interface and interactive media art.

Prem Seetharaman

Senior Research Scientist, Adobe Research

Prem is a Senior Research Scientist at Adobe Research, working in the Audio AI Lab. He received a PhD in 2019 at Northwestern University, advised by Bryan Pardo. Afterwards, he spent time at Descript where he worked on audio enhancement and generation. His recent work focuses on generative models for all types of audio, such as every-day sounds, music, and speech. He works at the intersection of computer audition, generative modeling, and interaction, with the goal of lowering the barrier to entry for content creation.

Mark Cartwright

Assistant Professor, New Jersey Institute of Technology, Department of Informatics

Mark Cartwright is Brooklyn-based computer scientist and musician. He joined New Jersey Institute of Technology as an Assistant Professor in the Department of Informatics in January 2021. His research lies at the intersection of human-computer interaction, audio signal processing, and machine learning. He completed his PhD in computer science at Northwestern University as a member of the Interactive Audio Lab.

Zafar Rafii

Audio Research Scientist, Audible Magic

Zafar Rafii is currently a research engineer at Gracenote. He received a Master of Science in Electrical Engineering from both Ecole Nationale Superieure de l’Electronique et de ses Applications (ENSEA) in France and Illinois Institute of Technology (IIT) in Chicago, and a PhD in Computer Science from Northwestern University. Some of the projects he has been working on are, among others, music genre classification, adaptive user interfaces, mono and stereo source separation, speech enhancement, audio fingerprinting and cover Identification.

Zhiyao Duan

Professor, Department of Electrical and Computer Engineering, University of Rochester

Zhiyao is an associate professor in the Department of Electrical and Computer Engineering at the University of Rochester since July 2013. He also holds a secondary appointment in the Department of Computer Science and is affiliated faculty of the Goergen Institute for Data Science.

Jinyu Han

Software Engineer, Facebook

Jinyu Han is a software engineer at Facebook. Prior to Facebook, Jinyu has worked at Amazon and Gracenote. He has also collaborated with researchers at Adobe. When he’s not coding, he’s raising a family and living the good life.

Erika Rumbold

Doctoral Student, University of Victoria

Erika completed her Computer Science masters student in the Interactive Audio Lab. She is now a doctoral student at the University of Victoria.

Noah Schaffer

Doctoral Student, Dartmouth

Noah completed his MS in computer science in 2022. While at Northwestern, he did work in source separation and generative modeling for audio. In his free time, he enjoys playing guitar and is a percussionist. In fall 2025 he begins PhD studies at Dartmouth.

Nathan Pruyne

Doctoral Student, Carnegie Mellon University

Nathan Pruyne did a double degree in Computer Science in the McCormick School of Engineering and Music Technology in the Bienen School of Music. He worked on HARP and data attribution for generative music models, and on speech analysis and editing. As of Fall 2025, he is a doctoral student at Carnegie Mellon University.

Cameron Churchwell

Doctoral Student, University of Illinois

Cameron Churchwell was an undergraduate who worked in the lab on on neural speech editing and pronunciation information. Today he is a doctoral student at the University of Illinois. [website]

Aldo Aguilar

MongoDB

Aldo graduated in 2022 with a Computer Science undergraduate degree and worked in the lab on designing deep learning-based accessible audio production tools. Aldo likes to spend his free time with his cat, playing the EWI, and reading and is now a big-shot at MongoDB.

Alisa Liu

PhD Candidate, University of Washington

Alisa graduated from Northwestern in spring 2020 with BA degrees in computer science and math, and identifies with the NLP and computer audition communities. She is now a doctoral student in computer science at the University of Washington. Her current interests include audio source separation, common sense reasoning, and text generation, among many other things.

Alex Fang

MM Piano, San Francisco Conservatory of Music

Alex graduated from Northwestern in fall 2019 with a BA/MS in computer science and a BM in piano performance. He is currently continuing his studies in piano as a graduate student at San Francisco Conservatory of Music. He is interested in incorporating music knowledge into building and evaluating music generation systems, and thinking about how technology can be integrated in music education.

Andreas Bugler

Chicago Trading Company

Andreas was an undergraduate student working towards a BS in computer science at Northwestern and graduated in 2022. He is interested in machine learning and music information retrieval. In his free time, he plays classical guitar and enjoys the outdoors.

Julia Wilkins

Doctoral Student, New York University

After working in the Interactive Audio Lab, Julia Wilkins became a Data Scientist/Engineer on the Product Data Team team at Sonos and is now getting her PhD at NYU. She is passionate about inspiring young women in Computer Science and animal welfare, and contributes to a range of volunteer organizations including the Microsoft TEALS teaching program and the Seattle Animal Shelter.