SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation
Zeyu Yang, Lai Wei, Roman Koshkin, Xi Chen, Satoshi Nakamura
Abstract
This work proposes a grammar-based chunking strategy that segments input streams into semantically complete units by parsing dependency relations (e.g., noun phrase boundaries, verb-object structures) and punctuation features. The method ensures chunk coherence and minimizes semantic fragmentation. Building on this mechanism, we present SASST (Syntax-Aware Simultaneous Translation), an end-to-end framework integrating frozen Whisper encoder and decoder-only LLM. The unified architecture dynamically outputs translation tokens or symbols to jointly optimize translation timing and content, with target-side reordering addressing word-order divergence. Experiments on CoVoST2 multilingual corpus (En to De/Zh/Ja) demonstrate significant translation quality improvements across languages, validating the effectiveness of syntactic structures in LLM-driven SimulST systems.
BibTeX
@inproceedings{aaai2026_sasstleveragings,
title = {SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation},
author = {Zeyu Yang and Lai Wei and Roman Koshkin and Xi Chen and Satoshi Nakamura},
booktitle = {AAAI 2026},
year = {2026}
}