@inproceedings{mieskes-benz-2023-h,
    title = "h{\_}da@{R}epro{H}umn {--} Reproduction of Human Evaluation and Technical Pipeline",
    author = "Mieskes, Margot  and
      Benz, Jacob Georg",
    editor = "Belz, Anya  and
      Popovi{\'c}, Maja  and
      Reiter, Ehud  and
      Thomson, Craig  and
      Sedoc, Jo{\~a}o",
    booktitle = "Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems",
    month = sep,
    year = "2023",
    address = "Varna, Bulgaria",
    publisher = "INCOMA Ltd., Shoumen, Bulgaria",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.humeval-1.11/",
    pages = "130--135",
    abstract = "How reliable are human evaluation results? Is it possible to replicate human evaluation? This work takes a closer look at the evaluation of the output of a Text-to-Speech (TTS) system. Unfortunately, our results indicate that human evaluation is not as straightforward to replicate as expected. Additionally, we also present results on reproducing the technical background of the TTS system and discuss potential reasons for the reproduction failure."
}