mlsanityData to 14 Oct 2026

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

arXiv 2508.07781 ↗First posted 11 Aug 2025cs.CLcited by 2

Not on the map. Why?

Abstract (arXiv)

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 Speech Translation), an end-to-end framework integrating frozen Whisper encoder and decoder-only LLM. The unified architecture dynamically outputs translation tokens or <WAIT> symbols to jointly optimize translation timing and content, with target-side reordering addressing word-order divergence. Experiments on CoVoST2 multilingual corpus En-{De, Zh, Ja} demonstrate significant translation quality improvements across languages and validate the effectiveness of syntactic structures in LLM-driven SimulST systems.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 24 of its 35 references that are in the map. First posted on arXiv 11 Aug 2025.

Builds on

24 of 35 references.

References · 24

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  3. 2020COMET: A Neural Framework for MT Evaluationcited by 1,033
  4. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 723
  5. 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
  6. 2020SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddingscited by 156
  7. 2017Sequence-to-Sequence Models Can Directly Translate Foreign Speechcited by 121
  8. 2016Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translationcited by 113
  9. 2020SimulEval: An Evaluation Toolkit for Simultaneous Translationcited by 94
  10. 2018Pre-training on high-resource speech recognition improves low-resource speech-to-text translationcited by 70
  11. 2021RealTranS: End-to-End Simultaneous Speech Translation with Convolutional Weighted-Shrinking Transformercited by 40
  12. 2022Information-Transport-based Policy for Simultaneous Translationcited by 40
12 more
  1. 2023AlignAtt: Using Attention-based Audio-Translation Alignments as a Guide for Simultaneous Speech Translationcited by 35
  2. 2024TransLLaMa: LLM-based Simultaneous Translation Systemcited by 34
  3. 2022Attention as a Guide for Simultaneous Speech Translationcited by 32
  4. 2020Streaming Simultaneous Speech Translation with Augmented Memory Transformercited by 30
  5. 2021Learning When to Translate for Streaming Speechcited by 30
  6. 2023End-to-End Simultaneous Speech Translation with Differentiable Segmentationcited by 22
  7. 2024StreamAtt: Direct Streaming Speech-to-Text Translation with Attention-based Audio History Selectioncited by 19
  8. 2025SeqPO-SiMT: Sequential Policy Optimization for Simultaneous Machine Translationcited by 13
  9. 2025Efficient and Adaptive Simultaneous Speech Translation with Fully Unidirectional Architecturecited by 12
  10. 2025StreamUni: Achieving Streaming Speech Translation with a Unified Large Speech-Language Modelcited by 6
  11. 2025SimulS2S-LLM: Unlocking Simultaneous Inference of Speech LLMs for Speech-to-Speech Translationcited by 3
  12. 2017Disentangling ASR and MT Errors in Speech Translationcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Modelscited by 3
  2. 2026Regularized Entropy Information Adaptation with Temporal-Awareness Networks for Simultaneous Speech Translationcited by 0