Yutong Wen

yutong12 [at] illinois [dot] edu

About

I am a second-year Ph.D. student in the Computer Science Department at the University of Illinois Urbana-Champaign, where I am advised by Prof. Minje Kim and Prof. Paris Smaragdis. Before my Ph.D. I was a undergraduate student at University of Rochester studying Audio and Music Engineering. I worked in the AIR lab advised by Prof. Zhiyao Duan.
   In research topics, I am interested in controllable audio generation and multi-condition source separation. My work explores how deep generative models can be guided by various control signals to synthesize audio or guide separation in a more flexible and expressive way.

News

  1. (June 2025) New music source separation paper accepted to ISMIR 2025. [link]

Publications

2025

User-Guided Generative Source Separation
Yutong Wen, Minje Kim, Paris Smaragdis
In Proc. of the 26th Int. Society for Music Information Retrieval Conf., Daejeon, South Korea, 2025.
[paper] [code] [website]

A Review on Score-based Generative Models for Audio Applications
Ge Zhu, Yutong Wen, Zhiyao Duan
Arxiv Preprint
[paper] [website]


2023

EDMSound: Spectrogram Based Diffusion Models for Efficient and High-Quality Audio Synthesis
Ge Zhu, Yutong Wen, Marc-André Carbonneau, Zhiyao Duan
37th Conference on Neural Information Processing Systems (2023) Machine Learning for Audio Workshop.
[paper] [code] [website]

Mitigating Cross-Database Differences for Learning Unified HRTF Representation
Yutong Wen, You Zhang, Zhiyao Duan
2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics October 22-25, 2023, New Paltz, NY
[paper] [code]