@inproceedings{yan-etal-2024-emofake,
title = "{E}mo{F}ake: An Initial Dataset for Emotion Fake Audio Detection",
author = "Yan, Zhao and
Jiangyan, Yi and
Jianhua, Tao and
Chenglong, Wang and
Yongfeng, Dong",
editor = "Sun, Maosong and
Liang, Jiye and
Han, Xianpei and
Liu, Zhiyuan and
He, Yulan",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.99/",
pages = "1286--1297",
language = "eng",
abstract = "{\textquotedblleft}To enhance the effectiveness of fake audio detection techniques, researchers have developed mul-tiple datasets such as those for the ASVspoof and ADD challenges. These datasets typically focuson capturing non-emotional characteristics in speech, such as the identity of the speaker and theauthenticity of the content. However, they often overlook changes in the emotional state of theaudio, which is another crucial dimension affecting the authenticity of speech. Therefore, thisstudy reports our progress in developing such an emotion fake audio detection dataset involvingchanging emotion state of the origin audio named EmoFake. The audio samples in EmoFake aregenerated using open-source emotional voice conversion models, intended to simulate potentialemotional tampering scenarios in real-world settings. We conducted a series of benchmark ex-periments on this dataset, and the results show that even advanced fake audio detection modelstrained on the ASVspoof 2019 LA dataset and the ADD 2022 track 3.2 dataset face challengeswith EmoFake. The EmoFake is publicly available1 now.{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yan-etal-2024-emofake">
<titleInfo>
<title>EmoFake: An Initial Dataset for Emotion Fake Audio Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhao</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Jiangyan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tao</namePart>
<namePart type="family">Jianhua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wang</namePart>
<namePart type="family">Chenglong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dong</namePart>
<namePart type="family">Yongfeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiye</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“To enhance the effectiveness of fake audio detection techniques, researchers have developed mul-tiple datasets such as those for the ASVspoof and ADD challenges. These datasets typically focuson capturing non-emotional characteristics in speech, such as the identity of the speaker and theauthenticity of the content. However, they often overlook changes in the emotional state of theaudio, which is another crucial dimension affecting the authenticity of speech. Therefore, thisstudy reports our progress in developing such an emotion fake audio detection dataset involvingchanging emotion state of the origin audio named EmoFake. The audio samples in EmoFake aregenerated using open-source emotional voice conversion models, intended to simulate potentialemotional tampering scenarios in real-world settings. We conducted a series of benchmark ex-periments on this dataset, and the results show that even advanced fake audio detection modelstrained on the ASVspoof 2019 LA dataset and the ADD 2022 track 3.2 dataset face challengeswith EmoFake. The EmoFake is publicly available1 now.”</abstract>
<identifier type="citekey">yan-etal-2024-emofake</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.99/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>1286</start>
<end>1297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EmoFake: An Initial Dataset for Emotion Fake Audio Detection
%A Yan, Zhao
%A Jiangyan, Yi
%A Jianhua, Tao
%A Chenglong, Wang
%A Yongfeng, Dong
%Y Sun, Maosong
%Y Liang, Jiye
%Y Han, Xianpei
%Y Liu, Zhiyuan
%Y He, Yulan
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G eng
%F yan-etal-2024-emofake
%X “To enhance the effectiveness of fake audio detection techniques, researchers have developed mul-tiple datasets such as those for the ASVspoof and ADD challenges. These datasets typically focuson capturing non-emotional characteristics in speech, such as the identity of the speaker and theauthenticity of the content. However, they often overlook changes in the emotional state of theaudio, which is another crucial dimension affecting the authenticity of speech. Therefore, thisstudy reports our progress in developing such an emotion fake audio detection dataset involvingchanging emotion state of the origin audio named EmoFake. The audio samples in EmoFake aregenerated using open-source emotional voice conversion models, intended to simulate potentialemotional tampering scenarios in real-world settings. We conducted a series of benchmark ex-periments on this dataset, and the results show that even advanced fake audio detection modelstrained on the ASVspoof 2019 LA dataset and the ADD 2022 track 3.2 dataset face challengeswith EmoFake. The EmoFake is publicly available1 now.”
%U https://aclanthology.org/2024.ccl-1.99/
%P 1286-1297
Markdown (Informal)
[EmoFake: An Initial Dataset for Emotion Fake Audio Detection](https://aclanthology.org/2024.ccl-1.99/) (Yan et al., CCL 2024)
ACL
- Zhao Yan, Yi Jiangyan, Tao Jianhua, Wang Chenglong, and Dong Yongfeng. 2024. EmoFake: An Initial Dataset for Emotion Fake Audio Detection. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), pages 1286–1297, Taiyuan, China. Chinese Information Processing Society of China.