@inproceedings{fedotova-etal-2024-constructing,
    title = "Constructing a Multimodal, Multilingual Translation and Interpreting Corpus: A Modular Pipeline and an Evaluation of {ASR} for Verbatim Transcription",
    author = "Fedotova, Alice  and
      Ferraresi, Adriano  and
      Mili{\v{c}}evi{\'c} Petrovi{\'c}, Maja  and
      Barr{\'o}n-Cede{\~n}o, Alberto",
    editor = "Dell'Orletta, Felice  and
      Lenci, Alessandro  and
      Montemagni, Simonetta  and
      Sprugnoli, Rachele",
    booktitle = "Proceedings of the 10th Italian Conference on Computational Linguistics (CLiC-it 2024)",
    month = dec,
    year = "2024",
    address = "Pisa, Italy",
    publisher = "CEUR Workshop Proceedings",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.clicit-1.42/",
    pages = "349--355",
    ISBN = "979-12-210-7060-6",
    abstract = "This paper presents a novel pipeline for constructing multimodal and multilingual parallel corpora, with a focus on evaluating state-of-the-art ASR tools for verbatim transcription. Our findings indicate that current technologies can streamline corpus construction, with fine-tuning showing promising results in terms of transcription quality compared to out-of-the-box Whisper models. The lowest overall WER achieved for English was 0.180, using a fine-tuned Whisper-small model. As for Italian, the fine-tuned Whisper-small model obtained a lower WER of 0.201 compared to the baseline Whisper-small{'}s WER of 0.219. While limitations remain, the updated pipeline is expected to drastically reduce the human efforts involved."
}