@inproceedings{an-etal-2024-investigation,
title = "An Investigation into Explainable Audio Hate Speech Detection",
author = "An, Jinmyeong and
Lee, Wonjun and
Jeon, Yejin and
Ok, Jungseul and
Kim, Yunsu and
Lee, Gary Geunbae",
editor = "Kawahara, Tatsuya and
Demberg, Vera and
Ultes, Stefan and
Inoue, Koji and
Mehri, Shikib and
Howcroft, David and
Komatani, Kazunori",
booktitle = "Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = sep,
year = "2024",
address = "Kyoto, Japan",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigdial-1.45",
pages = "533--543",
abstract = "Research on hate speech has predominantly revolved around the detection and interpretation from textual inputs, leaving verbal content largely unexplored. Moreover, while there has been some limited exploration into hate speech detection within verbal acoustic speech inputs, the aspect of interpretability has been overlooked. As such, we introduce a new task within the audio hate speech detection task domain - we specifically aim to identify specific time frames of hate speech within audio utterances. Towards this, we propose two different approaches, cascading and End-to-End (E2E). The first cascading approach initially converts audio to transcripts, identifies hate speech within these transcripts, and subsequently locates the corresponding audio time frames. Conversely, the second E2E approach processes audio utterances directly, which allows it to pinpoint hate speech within specific time frames. Moreover, due to the lack of explainable audio hate speech datasets that include frame-level rationales, we curated a synthetic audio dataset to train our models. We further validate these models on actual human speech utterances and we find that the E2E approach outperforms the cascading method in terms of audio frame Intersection over Union (IoU) metric. Furthermore, we observe that the inclusion of frame-level rationales significantly enhances hate speech detection accuracy for both E2E and cascading approaches.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="an-etal-2024-investigation">
<titleInfo>
<title>An Investigation into Explainable Audio Hate Speech Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinmyeong</namePart>
<namePart type="family">An</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wonjun</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yejin</namePart>
<namePart type="family">Jeon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungseul</namePart>
<namePart type="family">Ok</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunsu</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gary</namePart>
<namePart type="given">Geunbae</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tatsuya</namePart>
<namePart type="family">Kawahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vera</namePart>
<namePart type="family">Demberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Ultes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koji</namePart>
<namePart type="family">Inoue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shikib</namePart>
<namePart type="family">Mehri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Howcroft</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazunori</namePart>
<namePart type="family">Komatani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyoto, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Research on hate speech has predominantly revolved around the detection and interpretation from textual inputs, leaving verbal content largely unexplored. Moreover, while there has been some limited exploration into hate speech detection within verbal acoustic speech inputs, the aspect of interpretability has been overlooked. As such, we introduce a new task within the audio hate speech detection task domain - we specifically aim to identify specific time frames of hate speech within audio utterances. Towards this, we propose two different approaches, cascading and End-to-End (E2E). The first cascading approach initially converts audio to transcripts, identifies hate speech within these transcripts, and subsequently locates the corresponding audio time frames. Conversely, the second E2E approach processes audio utterances directly, which allows it to pinpoint hate speech within specific time frames. Moreover, due to the lack of explainable audio hate speech datasets that include frame-level rationales, we curated a synthetic audio dataset to train our models. We further validate these models on actual human speech utterances and we find that the E2E approach outperforms the cascading method in terms of audio frame Intersection over Union (IoU) metric. Furthermore, we observe that the inclusion of frame-level rationales significantly enhances hate speech detection accuracy for both E2E and cascading approaches.</abstract>
<identifier type="citekey">an-etal-2024-investigation</identifier>
<location>
<url>https://aclanthology.org/2024.sigdial-1.45</url>
</location>
<part>
<date>2024-09</date>
<extent unit="page">
<start>533</start>
<end>543</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Investigation into Explainable Audio Hate Speech Detection
%A An, Jinmyeong
%A Lee, Wonjun
%A Jeon, Yejin
%A Ok, Jungseul
%A Kim, Yunsu
%A Lee, Gary Geunbae
%Y Kawahara, Tatsuya
%Y Demberg, Vera
%Y Ultes, Stefan
%Y Inoue, Koji
%Y Mehri, Shikib
%Y Howcroft, David
%Y Komatani, Kazunori
%S Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2024
%8 September
%I Association for Computational Linguistics
%C Kyoto, Japan
%F an-etal-2024-investigation
%X Research on hate speech has predominantly revolved around the detection and interpretation from textual inputs, leaving verbal content largely unexplored. Moreover, while there has been some limited exploration into hate speech detection within verbal acoustic speech inputs, the aspect of interpretability has been overlooked. As such, we introduce a new task within the audio hate speech detection task domain - we specifically aim to identify specific time frames of hate speech within audio utterances. Towards this, we propose two different approaches, cascading and End-to-End (E2E). The first cascading approach initially converts audio to transcripts, identifies hate speech within these transcripts, and subsequently locates the corresponding audio time frames. Conversely, the second E2E approach processes audio utterances directly, which allows it to pinpoint hate speech within specific time frames. Moreover, due to the lack of explainable audio hate speech datasets that include frame-level rationales, we curated a synthetic audio dataset to train our models. We further validate these models on actual human speech utterances and we find that the E2E approach outperforms the cascading method in terms of audio frame Intersection over Union (IoU) metric. Furthermore, we observe that the inclusion of frame-level rationales significantly enhances hate speech detection accuracy for both E2E and cascading approaches.
%U https://aclanthology.org/2024.sigdial-1.45
%P 533-543
Markdown (Informal)
[An Investigation into Explainable Audio Hate Speech Detection](https://aclanthology.org/2024.sigdial-1.45) (An et al., SIGDIAL 2024)
ACL
- Jinmyeong An, Wonjun Lee, Yejin Jeon, Jungseul Ok, Yunsu Kim, and Gary Geunbae Lee. 2024. An Investigation into Explainable Audio Hate Speech Detection. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 533–543, Kyoto, Japan. Association for Computational Linguistics.