@inproceedings{xu-etal-2025-ca,
    title = "{CA}*: Addressing Evaluation Pitfalls in Computation-Aware Latency for Simultaneous Speech Translation",
    author = "Xu, Xi  and
      Xu, Wenda  and
      Ouyang, Siqi  and
      Li, Lei",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-naacl.393/",
    pages = "7062--7067",
    ISBN = "979-8-89176-195-7",
    abstract = "Simultaneous speech translation (SimulST) systems must balance translation quality with response time, making latency measurement crucial for evaluating their real-world performance. However, there has been a longstanding belief that current metrics yield unrealistically high latency measurements in unsegmented streaming settings. In this paper, we investigate this phenomenon, revealing its root cause in a fundamental misconception underlying existing latency evaluation approaches. We demonstrate that this issue affects not only streaming but also segment-level latency evaluation across different metrics. Furthermore, we propose a modification to correctly measure computation-aware latency for SimulST systems, addressing the limitations present in existing metrics."
}