SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (40) · 34358-34367
DOI: 10.1609/aaai.v40i40.40733 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Zeyu Yang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).
Abstract (Originalsprache)
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.
Zitieren
APA
Yang, Z., Wei, L., Koshkin, R., Chen, X., & Nakamura, S. (2026). SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(40), 34358-34367. https://doi.org/10.1609/aaai.v40i40.40733
Vancouver
Yang Z, Wei L, Koshkin R, Chen X, Nakamura S. SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(40):34358-34367. doi:10.1609/aaai.v40i40.40733
BibTeX
@article{Yang2026,
author = {Yang, Zeyu and Wei, Lai and Koshkin, Roman and Chen, Xi and Nakamura, Satoshi},
title = {SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {40},
pages = {34358--34367},
doi = {10.1609/aaai.v40i40.40733}
}
EUVIMED