@inproceedings{yang-nakamura-2026-cuhksz,
    title = "{CUHKSZ} Simultaneous Speech Translation System for {IWSLT} 2026",
    author = "Yang, Zeyu  and
      Nakamura, Satoshi",
    editor = "Salesky, Elizabeth  and
      Anastasopoulos, Antonios  and
      Negri, Matteo  and
      Federico, Marcello",
    booktitle = "Proceedings of the 23rd International Conference on Spoken Language Translation ({IWSLT} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, USA (in-person and online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/corrections-2026-06/2026.iwslt-1.13/",
    doi = "10.18653/v1/2026.iwslt-1.13",
    pages = "111--118",
    ISBN = "979-8-89176-411-8",
    abstract = "We present the CUHKSZ Team submission to the IWSLT 2026 Simultaneous Speech Translation evaluation, targeting the main and Extra Context tracks for English{\textrightarrow}{Chinese, German} on unsegmented speech. Our system is built upon Qwen3-Omni-30B-A3B, a natively aligned audio-text LLM. Under the Constrained condition, we apply LoRA adaptation exclusively to the LLM. Specifically, we construct syntax-aware, chunk-aligned supervision from existing ASR corpora, using Qwen3-30B-Instruct to synthesize target translations. This enables the model to internalize the simultaneous read/write policy by autonomously predicting {\ensuremath{<}}wait{\ensuremath{>}} tokens at semantically incomplete boundaries. With the policy internalized, execution is delegated to a lightweight streaming agent served via vLLM. This agent feeds audio in fixed chunks, manages a bounded dialogue history, and enforces strict emission controls to minimize computation-aware delay. For the sub-track, contextual priors are dynamically injected into the prompt. On the official dev set, our 0{--}2 s latency regime submissions achieve 40.5 BLEU (1.95 s) for En{\textrightarrow}Zh and 27.7 BLEU (1.72 s) for En{\textrightarrow}De. In the 2{--}4 s regime, performance scales to 42.1 BLEU (2.16 s) and 30.5 BLEU (2.29 s) respectively."
}