Metraipolis › archive › dc_cc4663940cd4

Quality-Aware Self-Correcting Speech Translation on an Edge Device — arXiv:2610.07545

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.07545
License (as archived)
CC0-1.0
Archived
2026-10-07T11:23:05.757Z
SHA-256 of the archived text
1f7ba893b2af9be9db5efaf91b15ff5c0ce07f5e53bbde80a2391d9678fc6c45
Stable URL of this page
https://metraipolis.com/documento/dc_cc4663940cd4

How to cite

Quality-Aware Self-Correcting Speech Translation on an Edge Device — arXiv:2610.07545 — arXiv (en), https://arxiv.org/abs/2610.07545 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cc4663940cd4 (Metraipolis archive dc_cc4663940cd4, sha256 1f7ba893b2af9be9db5efaf91b15ff5c0ce07f5e53bbde80a2391d9678fc6c45)
BibTeX
@misc{dccc4663940cd4,
  title = {Quality-Aware Self-Correcting Speech Translation on an Edge Device — arXiv:2610.07545},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.07545},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cc4663940cd4; sha256 1f7ba893b2af9be9db5efaf91b15ff5c0ce07f5e53bbde80a2391d9678fc6c45},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.07545. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We present a fully offline speech-to-speech translation pipeline that runs on a Jetson Nano (4 GB) and corrects its own weak translations without retraining. A Whisper-tiny ASR feeds an Opus-MT translator; multilingual BERT cosine similarity acts as a Quality Estimation (QE) gate, triggering a secondary-pass correction when confidence falls below a pre-defined threshold $\tau$. We compare three correction methods: QE reranking (M1), Minimum Bayes-Risk decoding (M2), and constrained beam search (M3). On 1,012 FLORES-200 sentences (English-Spanish), M2 at $\tau=0.90$ produces statistically significant improvements over greedy decoding on BLEU (+0.67, p<0.001), ChrF (+0.51, p<0.001), and COMET (+0.0020 at N=3, p=0.002); M1 yields no significant gains, and M3 is significantly worse than baseline (p>0.99). Our central finding is that QE functions effectively as a gate but poorly as a ranker: removing the QE model from candidate selection (M1$\to$M2) does not hurt quality and frees 680 MB from the critical path. Using a gain-to-edit ratio adapted from the post-editing-effort literature, we further show that smaller candidate pools (N=3) yield more surgical corrections with better semantic adequacy, while larger pools (N=10) maximise lexical reward. We release the system and demonstrate live translation across six language pairs.

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/2610.07545 — 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 2026-10-07T11:15:39.420Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).