Metraipolis › archive › dc_60eb5cb684c1
Reference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models — arXiv:2610.20763
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.20763
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T09:06:21.168Z
- SHA-256 of the archived text
d915002f85bb69acf8f8682e7ff32d2920963e393d08961dd4e94bebba00cc34- Stable URL of this page
https://metraipolis.com/documento/dc_60eb5cb684c1
How to cite
Reference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models — arXiv:2610.20763 — arXiv (en), https://arxiv.org/abs/2610.20763 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_60eb5cb684c1 (Metraipolis archive dc_60eb5cb684c1, sha256 d915002f85bb69acf8f8682e7ff32d2920963e393d08961dd4e94bebba00cc34)
BibTeX
@misc{dc60eb5cb684c1,
title = {Reference-Guided Turn-Taking Style Transfer for Full-Duplex Spoken Language Models — arXiv:2610.20763},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.20763},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_60eb5cb684c1; sha256 d915002f85bb69acf8f8682e7ff32d2920963e393d08961dd4e94bebba00cc34},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20763. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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 outside; none identifies the quantity that sets how much the model speaks. We identify it: a single late-layer residual-stream direction, the initiative vector, extracted from the model's own conversations without training or annotation. The same direction reads the decision, anticipating onsets up to 800 ms ahead, and shifts it: scaled during generation, it moves speech ratio from 6-12% to 42-61% (no steering: 21-30%), consistently across conversations, weights, and corpora. A short reference recording suffices to transfer a speaker's turn-taking style to the model, and the transfer is reference-specific: swapping in another speaker's reference worsens the match in 93-98% of cases, whereas the best uniform dose is indistinguishable from no steering. Turn-taking style is not frozen into the weights but a direction that can be read, shifted, and calibrated per person. Audio examples are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Sound (cs.SD). Pagina del lavoro: https://arxiv.org/abs/2610.20763 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T08:44:17.864Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).