Interspeech 2026 Papers Accepted

Three new papers are accepted for publication at Interspeech 2026! *Jaesung Bae, *Xiuwen Zheng, Minje Kim, Chang D. Yoo, and Mark Hasegawa-Johnson, “Something from Nothing: Data Augmentation for Robust Severity Level…
Yutong and Jocelyn Graduated

Yutong and Jocelyn Graduated

Yutong Wen and Jocelyn Xu graduated with their M.S. degrees in computer science. They have been such cool and fun students to work with, and it was my great pleasure…
ICASSP 2026

ICASSP 2026

My students and I spent a wonderful week at ICASSP 2026 in Barcelona. We presented 5 papers in various audio research areas, ranging from neural coding to speech separation and…

Facilitating Learning Excellence Award

I am honored to receive the "Facilitating Learning Excellence Award" from the Illinois Student Council. It's for my course, "CS545 Machine Learning for Signal Processing," I taught in Fall 2025.

HE-NAC

For paper submitted to IEEE Transactions on Audio, Speech, and Language Processing, titled "HE-NAC: High-Efficiency Neural Audio Coding via Hierarchical and Residual Multi-Band Quantization," by Darius Pétermann, Wootaek Lim, Seungkwon…

New Ph.D. Candidates

Jaesung, Jackie, and Cameron passed their qual exams and became Ph.D. candidates. Congratulations!

Talk at Adobe Research

I gave a talk at Adobe Research on recent neural coding projects I'm working on. It was nice to meet good old friends, although it was a remote talk.

Neural Speech and Audio Coding

Neural Speech and Audio Coding: A Research Thread Over the past several years, my group has been exploring a common question from multiple angles: how should we design neural speech…

arXiv Etiquette

Publishing on arxiv.org (or any other paper archiving services) has become an important part of research practice. Although using the service sounds straightforward, there are a few things to keep…

ICASSP 2026 Papers Accepted

I have been fortunate enough to work on the following interesting papers that were accepted for publication at ICASSP 2026. "From Hallucination to Articulation: Language Model-Driven Losses for Ultra Low-Bitrate…