collaborators

1 paper

eess.AS2026

NormToken: Speaker- and Duration-Normalized Semantic Speech Tokens via Iterative S2U-T2U Refinement

Hanlin Zhang, Daxin Tan, Dehua Tao +3

Semantic speech tokens should preserve linguistic content while suppressing utterance-specific acoustic and duration variation. However, existing speech-to-unit (S2U) tokenizers of…