Metraipolis › archive › dc_7be99181abcd

From Metrics to Natural Dialogue: French Full-Duplex Benchmark for Spoken Dialogue Models — arXiv:2609.10765

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.10765
License (as archived): CC0-1.0
Archived: 2026-10-16T07:17:39.104Z
SHA-256 of the archived text: a16eeb4cb34f9abf2a90f9bd0ae35f611c95b0c7386760256a4809a48c0b2789
Stable URL of this page: https://metraipolis.com/documento/dc_7be99181abcd

How to cite

From Metrics to Natural Dialogue: French Full-Duplex Benchmark for Spoken Dialogue Models — arXiv:2609.10765 — arXiv (en), https://arxiv.org/abs/2609.10765 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7be99181abcd (Metraipolis archive dc_7be99181abcd, sha256 a16eeb4cb34f9abf2a90f9bd0ae35f611c95b0c7386760256a4809a48c0b2789)

BibTeX

@misc{dc7be99181abcd,
  title = {From Metrics to Natural Dialogue: French Full-Duplex Benchmark for Spoken Dialogue Models — arXiv:2609.10765},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.10765},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7be99181abcd; sha256 a16eeb4cb34f9abf2a90f9bd0ae35f611c95b0c7386760256a4809a48c0b2789},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.10765. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Full-duplex spoken dialogue models aim to make voice agents more natural by allowing them to listen, speak, pause, and respond during ongoing conversation. However, it is not clear whether full-duplex benchmarks behave the same way when models are evaluated in a different language. To investigate this, we introduce a French full-duplex benchmark (FDB) with two variants, CALLFC-FDB for Canadian French and MEDIA-FDB for European French, and compare them with an English FDB. Built from real spoken resources, these benchmarks evaluate key full-duplex skills, including pause handling, turn-taking, backchannels, and interruptions. Beyond introducing French FDBs, we evaluate human--human conversations with FDB metrics to better understand the values these metrics take in real-world dialogue. Our analysis reveals that most timing-based metrics behave similarly across languages, while content-based evaluation degrades under language mismatch. We also find a trade-off between optimizing benchmark metrics and preserving conversational naturalness.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-11 in eess.AS).
Categorie arXiv: Audio and Speech Processing (eess.AS).
Pagina del lavoro: https://arxiv.org/abs/2609.10765 — 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 2026-10-16T06:59:25.285Z dalla pagina https://arxiv.org/catchup/eess.AS/2026-09-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).