Metraipolis › archive › dc_bec51684f915

Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue — arXiv:2609.03321

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.03321
License (as archived)
CC0-1.0
Archived
2026-10-17T01:40:14.313Z
SHA-256 of the archived text
5e0e4fcef89ca4779840e92bca571a88ac0d996ba76c463c8534df647e480b56
Stable URL of this page
https://metraipolis.com/documento/dc_bec51684f915

How to cite

Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue — arXiv:2609.03321 — arXiv (en), https://arxiv.org/abs/2609.03321 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bec51684f915 (Metraipolis archive dc_bec51684f915, sha256 5e0e4fcef89ca4779840e92bca571a88ac0d996ba76c463c8534df647e480b56)
BibTeX
@misc{dcbec51684f915,
  title = {Decoupling Turn-Taking from Semantics: A Decoupled Data Approach for Finite-State-Machine-Based Full-Duplex Dialogue — arXiv:2609.03321},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.03321},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bec51684f915; sha256 5e0e4fcef89ca4779840e92bca571a88ac0d996ba76c463c8534df647e480b56},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.03321. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The Neural Finite State Machine (NFSM) framework offers a pragmatic path to full-duplex dialogue by serializing turn-taking control and response generation onto a single causal tape under the standard next-token prediction objective, thereby preserving semantic prowess at a low fine-tuning cost. However, its reliance on synthetic text data fundamentally limits turn-taking naturalness, as Large Language Models (LLMs) cannot faithfully simulate the fine-grained acoustic temporal dynamics of real human dialogues. In this work, we propose a decoupled data approach that learns turn-taking from real Human-Human (HH) spoken dialogues while shaping semantic behavior through configurable Human-Agent (HA) text dialogues. To operationalize this approach, we introduce a rule-based event-guided data transformation method that serializes HH spoken dialogues into FSM tapes by classifying turn-taking events and applying deterministic mapping rules, enabling scalable supervision without LLM-generated annotations. We further propose a Source-Aware Calibrated (SAC) Loss that jointly calibrates the long-tailed distribution of state transition tokens and channels each data source toward the capability it best supervises. Experiments show that our approach substantially improves turn-taking proficiency while recovering the foundation LLM's semantic capability. Our code and model are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.03321 — 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 2026-10-17T01:11:43.518Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).