@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",
editor = "Dernoncourt, Franck and
Nguyen, Thien Huu and
Lai, Viet Dac and
Veyseh, Amir Pouran Ben and
Bui, Trung H. and
Yoon, David Seunghyun",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-nguyen-2022-investigating">
<titleInfo>
<title>Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Linh</namePart>
<namePart type="given">The</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dat</namePart>
<namePart type="given">Quoc</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop On Transcript Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Franck</namePart>
<namePart type="family">Dernoncourt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Huu</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viet</namePart>
<namePart type="given">Dac</namePart>
<namePart type="family">Lai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Amir</namePart>
<namePart type="given">Pouran</namePart>
<namePart type="given">Ben</namePart>
<namePart type="family">Veyseh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trung</namePart>
<namePart type="given">H</namePart>
<namePart type="family">Bui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">Seunghyun</namePart>
<namePart type="family">Yoon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, South Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">nguyen-nguyen-2022-investigating</identifier>
<location>
<url>https://aclanthology.org/2022.tu-1.5</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>34</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition
%A Nguyen, Linh The
%A Nguyen, Dat Quoc
%Y Dernoncourt, Franck
%Y Nguyen, Thien Huu
%Y Lai, Viet Dac
%Y Veyseh, Amir Pouran Ben
%Y Bui, Trung H.
%Y Yoon, David Seunghyun
%S Proceedings of the First Workshop On Transcript Understanding
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Gyeongju, South Korea
%F nguyen-nguyen-2022-investigating
%X 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.
%U https://aclanthology.org/2022.tu-1.5
%P 34-39
Markdown (Informal)
[Investigating the Impact of ASR Errors on Spoken Implicit Discourse Relation Recognition](https://aclanthology.org/2022.tu-1.5) (Nguyen & Nguyen, TU 2022)
ACL