@inproceedings{tatman-2017-gender,
    title = "Gender and Dialect Bias in {Y}ou{T}ube{'}s Automatic Captions",
    author = "Tatman, Rachael",
    editor = "Hovy, Dirk  and
      Spruit, Shannon  and
      Mitchell, Margaret  and
      Bender, Emily M.  and
      Strube, Michael  and
      Wallach, Hanna",
    booktitle = "Proceedings of the First {ACL} Workshop on Ethics in Natural Language Processing",
    month = apr,
    year = "2017",
    address = "Valencia, Spain",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W17-1606/",
    doi = "10.18653/v1/W17-1606",
    pages = "53--59",
    abstract = "This project evaluates the accuracy of YouTube{'}s automatically-generated captions across two genders and five dialect groups. Speakers' dialect and gender was controlled for by using videos uploaded as part of the ``accent tag challenge'', where speakers explicitly identify their language background. The results show robust differences in accuracy across both gender and dialect, with lower accuracy for 1) women and 2) speakers from Scotland. This finding builds on earlier research finding that speaker{'}s sociolinguistic identity may negatively impact their ability to use automatic speech recognition, and demonstrates the need for sociolinguistically-stratified validation of systems."
}