AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation

Zeyu Yang, Lai Wei, Roman Koshkin, Xi Chen, Satoshi Nakamura

AAAI 2026 · Large language models › Language, safety and interpretability · approach: Speech and audio language models · 4 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use syntax-aware chunking instead of fixed-length segmentation (ablation)SASST · CoVoST2 En-ZhBLEU: 23.2 -> 38.5Improved
use syntax-aware chunking instead of fixed-length segmentation (ablation)SASST · CoVoST2 En-Zhboundary alignment: 23% -> 82%Improved
use Qwen3-8B instead of LLaMA3-8B backbone (ablation)SASST · CoVoST2 En-ZhBLEU: 37.048 -> 40.216Improved
use Qwen3-8B instead of LLaMA3-8B backbone (ablation)SASST · CoVoST2 En-DeBLEU: 26.684 -> 27.892Improved
use Qwen3-8B instead of LLaMA3-8B backbone (ablation)SASST · CoVoST2 En-JaBLEU: 25.674 -> 27.279Improved
increase input chunk size (latency from ~1.8 s to ~4.0 s) (ablation)SASST · CoVoST2 En-ZhBLEU: 34.1 -> 41.5Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy