Metraipolis › archive › dc_20d3a0785dfb

AutoTerm-SST: Adaptive Terminology Memory with Zero Session-Time Setup for Streaming Speech Translation — arXiv:2610.26865

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.26865
License (as archived)
CC0-1.0
Archived
2026-10-21T07:08:41.441Z
SHA-256 of the archived text
2cb1ed0258a594a643ad9a9aa8609df3fd485762dda9057a36016ec744e02ea8
Stable URL of this page
https://metraipolis.com/documento/dc_20d3a0785dfb

How to cite

AutoTerm-SST: Adaptive Terminology Memory with Zero Session-Time Setup for Streaming Speech Translation — arXiv:2610.26865 — arXiv (en), https://arxiv.org/abs/2610.26865 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_20d3a0785dfb (Metraipolis archive dc_20d3a0785dfb, sha256 2cb1ed0258a594a643ad9a9aa8609df3fd485762dda9057a36016ec744e02ea8)
BibTeX
@misc{dc20d3a0785dfb,
  title = {AutoTerm-SST: Adaptive Terminology Memory with Zero Session-Time Setup for Streaming Speech Translation — arXiv:2610.26865},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.26865},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_20d3a0785dfb; sha256 2cb1ed0258a594a643ad9a9aa8609df3fd485762dda9057a36016ec744e02ea8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.26865. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Retrieval-augmented speech translation improves rare terminology, but systems such as RASST still assume that users provide a glossary before each session. That assumption is inconvenient for live talks, while merging every domain into one growing glossary eventually places too many irrelevant terms in the same retrieval and prompt competition. We present AutoTerm-SST, an interactive system that removes session-time glossary upload and domain selection. It organizes a large offline terminology catalog into topic slices, matches recent streaming translation context to bilingual slice prototypes, and activates a compact multi-slice working set under fixed retrieval and prompt budgets. On five ACL and five ESO oncology talks, AutoTerm matches a known-domain reference in terminology accuracy (88.3% vs. 88.1%) and mWER-resegmented BLEU (45.09 vs. 45.19), while requiring no domain input. Compared with a one-million-entry merged glossary, it improves terminology accuracy by 3.9 points and BLEU by 2.30. Routing plus four-slice retrieval remains lightweight: the complete system runs at 0.406 RTF, and the vLLM host sustains 32 real-time sessions. The live demo exposes active slices and retrieved terminology as the topic changes, providing zero-setup terminology-aware streaming translation.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2610.26865 — 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 2026-10-21T07:05:58.084Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).