Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition

                                                            @inproceedings{nguyen-nguyen-2022-investigating,
    title = "Investigating the Impact of {ASR} Errors on Spoken Implicit Discourse Relation Recognition",
    author = "Nguyen, Linh The  and
      Nguyen, Dat Quoc",
    booktitle = "Proceedings of the First Workshop On Transcript Understanding",
    month = oct,
    year = "2022",
    address = "Gyeongju, South Korea",
    publisher = "International Conference on Computational Linguistics",
    url = "https://aclanthology.org/2022.tu-1.5",
    pages = "34--39",
    abstract = "We present an empirical study investigating the influence of automatic speech recognition (ASR) errors on the spoken implicit discourse relation recognition (IDRR) task. We construct a spoken dataset for this task based on the Penn Discourse Treebank 2.0. On this dataset, we conduct {``}Cascaded{''} experiments employing state-of-the-art ASR and text-based IDRR models and find that the ASR errors significantly decrease the IDRR performance. In addition, the {``}Cascaded{''} approach does remarkably better than an {``}End-to-End{''} one that directly predicts a relation label for each input argument speech pair.",
}