@inproceedings{ali-renals-2018-word,
    title = "Word Error Rate Estimation for Speech Recognition: e-{WER}",
    author = "Ali, Ahmed  and
      Renals, Steve",
    editor = "Gurevych, Iryna  and
      Miyao, Yusuke",
    booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)",
    month = jul,
    year = "2018",
    address = "Melbourne, Australia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/P18-2004/",
    doi = "10.18653/v1/P18-2004",
    pages = "20--24",
    abstract = "Measuring the performance of automatic speech recognition (ASR) systems requires manually transcribed data in order to compute the word error rate (WER), which is often time-consuming and expensive. In this paper, we propose a novel approach to estimate WER, or e-WER, which does not require a gold-standard transcription of the test set. Our e-WER framework uses a comprehensive set of features: ASR recognised text, character recognition results to complement recognition output, and internal decoder features. We report results for the two features; black-box and glass-box using unseen 24 Arabic broadcast programs. Our system achieves 16.9{\%} WER root mean squared error (RMSE) across 1,400 sentences. The estimated overall WER e-WER was 25.3{\%} for the three hours test set, while the actual WER was 28.5{\%}."
}