September 20, 2022 Natural Language Processing

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

  • 26 minutes
  • Linh The Nguyen and Dat Quoc Nguyen

  • Workshop On Transcript Understanding 2022
Share

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.

Bibtex

@inproceedings{sidrr,
title = {{Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition}},
author = {Linh The Nguyen and Dat Quoc Nguyen},
booktitle = {Proceedings of the first Workshop On Transcript Understanding},
year = {2022}
}

Back to Research
  • 26 minutes
  • Linh The Nguyen and Dat Quoc Nguyen

  • Workshop On Transcript Understanding 2022
Share

Related publications