Metraipolis › archive › dc_f1a208fb17fa

Simultaneous Translation between Sign Languages — arXiv:2609.35608

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35608
License (as archived)
CC0-1.0
Archived
2026-10-07T21:54:20.111Z
SHA-256 of the archived text
dfbdbb5236ed9e9345783771bf1cafddcdd1e496e46a4f7f887b15b75a10f842
Stable URL of this page
https://metraipolis.com/documento/dc_f1a208fb17fa

How to cite

Simultaneous Translation between Sign Languages — arXiv:2609.35608 — arXiv (en), https://arxiv.org/abs/2609.35608 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f1a208fb17fa (Metraipolis archive dc_f1a208fb17fa, sha256 dfbdbb5236ed9e9345783771bf1cafddcdd1e496e46a4f7f887b15b75a10f842)
BibTeX
@misc{dcf1a208fb17fa,
  title = {Simultaneous Translation between Sign Languages — arXiv:2609.35608},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35608},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f1a208fb17fa; sha256 dfbdbb5236ed9e9345783771bf1cafddcdd1e496e46a4f7f887b15b75a10f842},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35608. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deaf and hard-of-hearing (DHH) signers cannot converse in real time across different sign languages today: existing sign-to-sign translation systems run offline, requiring the full source clip before any target sign is emitted. Live use cases - e.g. broadcast interpretation and two-way video calls - instead demand simultaneous output, while the source signer is still signing. We present, to our knowledge, the first simultaneous sign-to-sign (S2S) translation system, with two wait-k regimes: test-time wait-k inference applied directly to a full-sentence model, and a trained wait-k model via stochastic multi-path supervision. We further introduce ca-Stream-AL, a computation-aware latency metric for streaming output. Averaged across six S2S directions on both a smaller human-verified test set and a larger synthetic S2S corpus, our streaming system achieves a 38% ca-Stream-AL reduction while staying within a 9% DTW-PA-MPJPE increase and a 2.1 BLEU-4 drop compared to the full-sentence baseline. A word-order case study probes how the streaming model handles word order mismatch between different sign languages - a consequence of simultaneous translation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CL).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.35608 — 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 2026-10-07T21:27:08.848Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).