@inproceedings{huber-etal-2023-end,
    title = "End-to-End Evaluation for Low-Latency Simultaneous Speech Translation",
    author = "Huber, Christian  and
      Dinh, Tu Anh  and
      Mullov, Carlos  and
      Pham, Ngoc-Quan  and
      Nguyen, Thai Binh  and
      Retkowski, Fabian  and
      Constantin, Stefan  and
      Ugan, Enes  and
      Liu, Danni  and
      Li, Zhaolin  and
      Koneru, Sai  and
      Niehues, Jan  and
      Waibel, Alexander",
    editor = "Feng, Yansong  and
      Lefever, Els",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.emnlp-demo.2",
    doi = "10.18653/v1/2023.emnlp-demo.2",
    pages = "12--20",
    abstract = "The challenge of low-latency speech translation has recently draw significant interest in the research community as shown by several publications and shared tasks. Therefore, it is essential to evaluate these different approaches in realistic scenarios. However, currently only specific aspects of the systems are evaluated and often it is not possible to compare different approaches. In this work, we propose the first framework to perform and evaluate the various aspects of low-latency speech translation under realistic conditions. The evaluation is carried out in an end-to-end fashion. This includes the segmentation of the audio as well as the run-time of the different components. Secondly, we compare different approaches to low-latency speech translation using this framework. We evaluate models with the option to revise the output as well as methods with fixed output. Furthermore, we directly compare state-of-the-art cascaded as well as end-to-end systems. Finally, the framework allows to automatically evaluate the translation quality as well as latency and also provides a web interface to show the low-latency model outputs to the user.",
}