10 papers
PACT: A Pragmatic Prompting Framework for Expressive and Voice-Preserving Speech-to-Speech Translation
Yuchen Song, Satoshi Nakamura
Speech-to-speech translation should preserve not only what is said, but also who says it and how it is said. Existing end-to-end S2ST, speech MLLM, and cascade systems can preserve…
MuLA-Bench: A Multilingual Long-Form Audio Understanding Benchmark via Multi-Tier Auditing
Zeyu Yang, Xinyu Zhang, Zibo Bi +5
Long-form audio performance is often summarized by context length and aggregate accuracy, obscuring how language, evidence, and task jointly shape difficulty. We introduce MuLA-Ben…
When to Use Extra Context: Evidence-Grounded Terminology Adaptation for Simultaneous Speech Translation
Zeyu Yang, Satoshi Nakamura
Extra context is valuable for simultaneous speech translation of technical talks, but injecting the entire document context into every streaming segment is often too coarse. Throug…
Evaluating and Preserving Lexical Stress in English-to-Chinese Speech-to-Speech Translation
Yuchen Song, Xi Chen, Mingze Li +1
Speech-to-speech translation (S2ST) systems have achieved impressive progress in semantic accuracy and speech naturalness. However, the cross-lingual transfer of lexical stress, a…
Leveraging Audio-LLMs to Filter Speech-to-Speech Training Data
Qixu Chen, Satoshi Nakamura
Large-scale mined corpora provide abundant training data for end-to-end speech-to-speech translation (S2ST) but may contain noise, misalignment, and semantic errors. Filtering nois…
Starlink Constellation: Deployment, Configuration, and Dynamics
Muaz Ali, Utkarsh Upadhyay, Sean McCormick +2
Starlink has rapidly emerged as the world's largest satellite constellation and the de facto reference system for low Earth orbit (LEO) networking research. Existing literature pre…
Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies
Qianen Zhang, Zeyu Yang, Satoshi Nakamura
Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional policies with only READ/WRITE actions cannot fully…
DPO-Tuned Large Language Models for Segmentation in Simultaneous Speech Translation
Zeyu Yang, Satoshi Nakamura
Simultaneous speech translation requires accurate segmentation to balance translation quality and latency. Recent studies such as SHAS have introduced pretrained segmentation model…
Redefining Machine Simultaneous Interpretation: From Incremental Translation to Human-Like Strategies
Qianen Zhang, Satoshi Nakamura
Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional encoder-decoder policies with only READ/WRITE actio…
SASST: Leveraging Syntax-Aware Chunking and LLMs for Simultaneous Speech Translation
Zeyu Yang, Lai Wei, Roman Koshkin +2
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, ver…