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…
Haici Yang Defended

Haici Yang Defended

Haici Yang defended her dissertation ("Latent Variable Learning for Generative Neural Audio Codecs") successfully!
WASPAA 2025 in Lake Tahoe

WASPAA 2025 in Lake Tahoe

My group in Illinois, former students at IU, and collaborators have had a strong presence at WASPAA 2025, which was one of the best conference experiences I've had so far.…
ISMIR 2025 in Daejeon, Korea

ISMIR 2025 in Daejeon, Korea

ISMIR 2025 in Daejeon, Korea was really fun. Learned a lot from the nice papers, how things are organized there, and enjoyed the music so much. Yutong Wen presented a…

AD-FlowTSE

Tsun-An Hsieh and Minje Kim, "Adaptive Deterministic Flow Matching for Target Speaker Extraction," Under Review for Publication at ICASSP 2026 Sound Examples: https://alexiehta.github.io/demo/ad_flowtse/ad_flowtse_demo.html Github Repo: https://github.com/aleXiehta/AD-FlowTSE