Metraipolis › archive › dc_a3e9085ff4be

Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech — arXiv:2608.16053

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.16053
License (as archived)
CC0-1.0
Archived
2026-10-18T18:58:54.554Z
SHA-256 of the archived text
76dec3884113d21c5b3b8b1127a489588e2f75ef165e37757e2e71225418ce18
Stable URL of this page
https://metraipolis.com/documento/dc_a3e9085ff4be

How to cite

Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech — arXiv:2608.16053 — arXiv (en), https://arxiv.org/abs/2608.16053 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a3e9085ff4be (Metraipolis archive dc_a3e9085ff4be, sha256 76dec3884113d21c5b3b8b1127a489588e2f75ef165e37757e2e71225418ce18)
BibTeX
@misc{dca3e9085ff4be,
  title = {Agentic-DuplexGen: Decoupling Content, Timing, and Acoustics for Synthetic Dialogue Speech — arXiv:2608.16053},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.16053},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a3e9085ff4be; sha256 76dec3884113d21c5b3b8b1127a489588e2f75ef165e37757e2e71225418ce18},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.16053. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Synthetic conversational speech has become an important resource for developing and evaluating conversational speech systems. However, existing dialogue synthesis pipelines typically generate dialogue content first and then insert interruptions, overlap, and backchannels using handcrafted markers or timing rules, making conversational timing prescribed rather than interaction-driven. We present Agentic-DuplexGen, a dialogue synthesis framework that explicitly decouples content, timing, and acoustics. An LLM first generates the dialogue script, and then two full-duplex conversational models perform the script while listening to each other in real time. This allows conversational timing to emerge naturally while preserving the scripted content. Finally, a high-fidelity text-to-speech model re-renders the interaction without altering its timing. As a demonstration of the proposed framework, we construct a patient--clinician conversational speech corpus with construction-time annotations, including word timestamps, speaker activity, overlap regions, and interaction events. Experimental results show that the proposed framework produces conversational dynamics closer to real dialogue than conventional stitching-based synthesis.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL) ; Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2608.16053 — 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 2026-10-18T18:06:57.879Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).