@inproceedings{grigoryan-etal-2026-nemo,
    title = "{N}e{M}o@{IWSLT} 2026: Cascaded System for Simultaneous Speech Translation",
    author = "Grigoryan, Lilit  and
      Bataev, Vladimir  and
      Andrusenko, Andrei  and
      Hrinchuk, Oleksii  and
      Karamyan, Davit  and
      Albasiri, Enas  and
      Lavrukhin, Vitaly  and
      Karpov, Nikolay  and
      Ginsburg, Boris",
    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-1.23/",
    doi = "10.18653/v1/2026.iwslt-1.23",
    pages = "204--211",
    ISBN = "979-8-89176-411-8",
    abstract = "This paper describes the NVIDIA NeMo team{'}s submission to the IWSLT 2026 Simultaneous Speech Translation (SimulST) tracks. We use a cascaded architecture combining a dual-mode Unified ASR Transducer model with a multilingual Large Language Model (LLM). The ASR is trained to deliver stable transcriptions across wide range of latencies, providing a reliable foundation for high-quality LLM translation. Our submission participates in the English{--}German, English{--}Italian, and English{--}Chinese tasks, in both standard and contextualized settings, as well as the Czech{--}English standard track, covering both low- and high-latency scenarios. We further analyze how ASR and LLM design choices affect the system{'}s overall latency and translation quality."
}