Reference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models
arXiv:2610.20763v1 Announce Type: new Abstract: Full-duplex spoken language models decide at every frame whether to take the floor, defining a conversational personality -- yet each set of weights encodes exactly one, which human speakers bracket rather than share. Existing controls mostly act from…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-16 04:00 · arXiv cs.CL
Reference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models