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 Estimation of Dysarthric Speech,” Long Paper Track (* Equal contribution) [pdf, GitHub, HuggingFace] - Dimitrios Bralios, Paris Smaragdis, and Minje Kim, “Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding” [pdf]
- Inseon Jang, Minje Kim, Wootaek Lim, and Seungkwon Beack, “End-to-End Model Compression for Personalized Neural Speech Codecs” [pdf, demo]