Showing eess.ASShow all
3 papers · 1 filter
eess.AS2026
Unsupervised Speech Recognition at the Syllable Level
Liming Wang, Kai-Wei Chang, Kunio Kashino +3
Training speech recognizers with unpaired speech and text -- known as unsupervised speech recognition (UASR) -- is a crucial step toward extending ASR to low-resource languages in…
eess.AS2026
Do Multimodal Large Language Models Need Reasoning to Classify Dementia from Speech?
Liming Wang, Neguine Rezaii, Bradford C. Dickerson +1
Multimodal large language models (MLLMs) have emerged as a promising approach for improving the accuracy, transferability, and explainability of automatic dementia classification (…
eess.AS2026
DDPO-VC: Speaker De-Identification via Diffusion Denoising Policy Optimization
Liming Wang, Cody Karjadi, Rhoda Au +1
A key challenge of speaker de-identification is the balance between privacy and utility. Many utility variables, such as the cognitive health status of the speaker, are correlated…