Metraipolis › archive › dc_7212e7ed3acb

TurnFSM for Full-Duplex Dialogue System: Internalizing State-Machine Logic for Streaming Semantic Voice Activity Detection and Utterance-Level Rejection — arXiv:2609.04240

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.04240
License (as archived)
CC0-1.0
Archived
2026-10-17T00:43:25.687Z
SHA-256 of the archived text
34ca76bad60a1f8fe97f768cbbe6ae9ad58073f8d96f0556e15d642ed4343f73
Stable URL of this page
https://metraipolis.com/documento/dc_7212e7ed3acb

How to cite

TurnFSM for Full-Duplex Dialogue System: Internalizing State-Machine Logic for Streaming Semantic Voice Activity Detection and Utterance-Level Rejection — arXiv:2609.04240 — arXiv (en), https://arxiv.org/abs/2609.04240 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7212e7ed3acb (Metraipolis archive dc_7212e7ed3acb, sha256 34ca76bad60a1f8fe97f768cbbe6ae9ad58073f8d96f0556e15d642ed4343f73)
BibTeX
@misc{dc7212e7ed3acb,
  title = {TurnFSM for Full-Duplex Dialogue System: Internalizing State-Machine Logic for Streaming Semantic Voice Activity Detection and Utterance-Level Rejection — arXiv:2609.04240},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.04240},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7212e7ed3acb; sha256 34ca76bad60a1f8fe97f768cbbe6ae9ad58073f8d96f0556e15d642ed4343f73},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.04240. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Full-duplex voice assistants must continuously listen while speaking, handling user interruptions under low-latency and resource-constrained streaming conditions. Existing end-to-end full-duplex models can compromise reasoning-related capabilities after speech-domain adaptation, whereas cascaded pipelines introduce extra inference overhead and handcrafted control logic. We propose TurnFSM, an LLM-based state prediction framework that internalizes turn control as explicit finite-state transitions, unifying streaming semantic VAD and utterance-level rejection. TurnFSM decomposes submission and rejection into a serial decision process, reducing multi-task interference while maintaining performance comparable to single-task models. We further introduce a first-order state transition mechanism that enforces the dependency on only the previous state during training, enabling compact inference with the standard causal mask and original LLM positional encoding while avoiding historical state-token accumulation and unnecessary step-by-step state generation. Experimental results show that TurnFSM consistently outperforms the binary-head baseline and remains competitive with task-specific models.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-07 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.04240 — 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 2026-10-17T00:21:40.220Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).