Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation
arXiv:2610.02612v1 Announce Type: new Abstract: Simultaneous speech translation must emit useful target text before the source is complete while preserving every committed token. We adapt a full-utterance speech language model using prefix supervision derived from its own complete- and partial-wave…
Read the full story at arXiv cs.CL ↗
Timeline · 1 report
- 2026-10-05 04:00 · arXiv cs.CL
Learning When to Commit from Partial Speech for End-to-End Simultaneous Speech Translation