Metraipolis › archive › dc_d19035930055

Less can be More: What Aspects of Speech Drive End-of-Turn Detection — arXiv:2609.11066

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.11066
License (as archived)
CC0-1.0
Archived
2026-10-16T05:26:49.060Z
SHA-256 of the archived text
7323d382f1c1e27dd6662da2b3b9a0273c6a472df3709dc32fdafdf26f45065d
Stable URL of this page
https://metraipolis.com/documento/dc_d19035930055

How to cite

Less can be More: What Aspects of Speech Drive End-of-Turn Detection — arXiv:2609.11066 — arXiv (en), https://arxiv.org/abs/2609.11066 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d19035930055 (Metraipolis archive dc_d19035930055, sha256 7323d382f1c1e27dd6662da2b3b9a0273c6a472df3709dc32fdafdf26f45065d)
BibTeX
@misc{dcd19035930055,
  title = {Less can be More: What Aspects of Speech Drive End-of-Turn Detection — arXiv:2609.11066},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.11066},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d19035930055; sha256 7323d382f1c1e27dd6662da2b3b9a0273c6a472df3709dc32fdafdf26f45065d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.11066. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In conversational AI, detecting when a speaker has finished talking is crucial for natural turn taking. While recent work incorporates semantics, the relative contribution of different modalities remains unclear. We present a controlled ablation of acoustic, prosodic, and semantic signals for streaming end of turn detection using a lightweight trimodal classifier. Under identical training conditions, the acoustic prosodic combination achieves the best balance of accuracy and latency, achieving utterance F1 of 0.93 with 7.8% false alarms at 400ms median latency. Adding text increases premature detections without improving performance. Feature space analysis confirms that prosodic features have the strongest class separability, while text representations overlap substantially. These findings suggest that turn-taking is primarily conveyed through intonation and silence patterns rather than semantic completeness, enabling faster and more reliable systems without expensive text inference.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in cs.AI).
Categorie arXiv: Audio and Speech Processing (eess.AS) ; Artificial Intelligence (cs.AI); Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.11066 — 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 2026-10-16T05:17:52.118Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).