SEMACS: Semantic–Acoustic Speech Coding for Ultra-Low Token Rates
Jan 1, 2026·,
,·
1 min read
Tu Nguyen
Thoai Bui
Dat Viet Thanh Nguyen
Dat Ngo
Abstract
A speech coding approach that jointly models semantic and acoustic representations to reach ultra-low token rates. Manuscript currently under review — details will be posted once the paper is public.
Type
Publication
Manuscript under review
This manuscript is currently under review. A link to the preprint, code, and full details will be added here once it is publicly available.
