An Improved System for Partially Fake Audio Detection Using Pre-trained Model

Jianqian Zhang; Hanyue Liu; Mengyuan Deng; Jing Wang; Yi Sun; Liang Xu; Jiahao Li

doi:10.1007/978-981-97-0601-3_30

An Improved System for Partially Fake Audio Detection Using Pre-trained Model

Jianqian Zhang, Hanyue Liu, Mengyuan Deng, Jing Wang^*, Yi Sun, Liang Xu, Jiahao Li

^*Corresponding author for this work

School of Information and Electronics

Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The technology of speech synthesis and conversion has made good progress with the development of deep learning. However, such technology can also do harm to information security and may be applied for illegal uses. Therefore, researchers have conducted a lot of research on the task of speech deep forgery detection recently. Corresponding to this, the Audio Deep Synthesis Detection Challenge 2023 (ADD 2023) is held. In this paper, we propose a fake audio detecting system using a pre-trained model, focusing on partially fake audio detection tasks. We have presented our models to the ADD 2023 challenge. In the final competition, our system got a score of 0.4855 in the manipulation region location track.

Original language	English
Title of host publication	Man-Machine Speech Communication - 18th National Conference, NCMMSC 2023, Proceedings
Editors	Jia Jia, Zhenhua Ling, Xie Chen, Ya Li, Zixing Zhang
Publisher	Springer Science and Business Media Deutschland GmbH
Pages	346-353
Number of pages	8
ISBN (Print)	9789819706006
DOIs	https://doi.org/10.1007/978-981-97-0601-3_30
Publication status	Published - 2024
Event	18th National Conference on Man-Machine Speech Communication, NCMMSC 2023 - Suzhou, China Duration: 8 Dec 2023 → 11 Dec 2023

Publication series

Name	Communications in Computer and Information Science
Volume	2006
ISSN (Print)	1865-0929
ISSN (Electronic)	1865-0937

Conference

Conference	18th National Conference on Man-Machine Speech Communication, NCMMSC 2023
Country/Territory	China
City	Suzhou
Period	8/12/23 → 11/12/23

Keywords

audio deepfake detection
deep-learning
fake region location
manipulation

Access to Document

10.1007/978-981-97-0601-3_30

Cite this

Zhang, J., Liu, H., Deng, M., Wang, J., Sun, Y., Xu, L., & Li, J. (2024). An Improved System for Partially Fake Audio Detection Using Pre-trained Model. In J. Jia, Z. Ling, X. Chen, Y. Li, & Z. Zhang (Eds.), Man-Machine Speech Communication - 18th National Conference, NCMMSC 2023, Proceedings (pp. 346-353). (Communications in Computer and Information Science; Vol. 2006). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-981-97-0601-3_30

Zhang, Jianqian ; Liu, Hanyue ; Deng, Mengyuan et al. / An Improved System for Partially Fake Audio Detection Using Pre-trained Model. Man-Machine Speech Communication - 18th National Conference, NCMMSC 2023, Proceedings. editor / Jia Jia ; Zhenhua Ling ; Xie Chen ; Ya Li ; Zixing Zhang. Springer Science and Business Media Deutschland GmbH, 2024. pp. 346-353 (Communications in Computer and Information Science).

@inproceedings{f81731ee736546eaae43ee4da744ce7c,

title = "An Improved System for Partially Fake Audio Detection Using Pre-trained Model",

abstract = "The technology of speech synthesis and conversion has made good progress with the development of deep learning. However, such technology can also do harm to information security and may be applied for illegal uses. Therefore, researchers have conducted a lot of research on the task of speech deep forgery detection recently. Corresponding to this, the Audio Deep Synthesis Detection Challenge 2023 (ADD 2023) is held. In this paper, we propose a fake audio detecting system using a pre-trained model, focusing on partially fake audio detection tasks. We have presented our models to the ADD 2023 challenge. In the final competition, our system got a score of 0.4855 in the manipulation region location track.",

keywords = "audio deepfake detection, deep-learning, fake region location, manipulation",

author = "Jianqian Zhang and Hanyue Liu and Mengyuan Deng and Jing Wang and Yi Sun and Liang Xu and Jiahao Li",

note = "Publisher Copyright: {\textcopyright} The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.; 18th National Conference on Man-Machine Speech Communication, NCMMSC 2023 ; Conference date: 08-12-2023 Through 11-12-2023",

year = "2024",

doi = "10.1007/978-981-97-0601-3\_30",

language = "English",

isbn = "9789819706006",

series = "Communications in Computer and Information Science",

publisher = "Springer Science and Business Media Deutschland GmbH",

pages = "346--353",

editor = "Jia Jia and Zhenhua Ling and Xie Chen and Ya Li and Zixing Zhang",

booktitle = "Man-Machine Speech Communication - 18th National Conference, NCMMSC 2023, Proceedings",

address = "Germany",

}

Zhang, J, Liu, H, Deng, M, Wang, J, Sun, Y, Xu, L & Li, J 2024, An Improved System for Partially Fake Audio Detection Using Pre-trained Model. in J Jia, Z Ling, X Chen, Y Li & Z Zhang (eds), Man-Machine Speech Communication - 18th National Conference, NCMMSC 2023, Proceedings. Communications in Computer and Information Science, vol. 2006, Springer Science and Business Media Deutschland GmbH, pp. 346-353, 18th National Conference on Man-Machine Speech Communication, NCMMSC 2023, Suzhou, China, 8/12/23. https://doi.org/10.1007/978-981-97-0601-3_30

An Improved System for Partially Fake Audio Detection Using Pre-trained Model. / Zhang, Jianqian; Liu, Hanyue; Deng, Mengyuan et al.
Man-Machine Speech Communication - 18th National Conference, NCMMSC 2023, Proceedings. ed. / Jia Jia; Zhenhua Ling; Xie Chen; Ya Li; Zixing Zhang. Springer Science and Business Media Deutschland GmbH, 2024. p. 346-353 (Communications in Computer and Information Science; Vol. 2006).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - An Improved System for Partially Fake Audio Detection Using Pre-trained Model

AU - Zhang, Jianqian

AU - Liu, Hanyue

AU - Deng, Mengyuan

AU - Wang, Jing

AU - Sun, Yi

AU - Xu, Liang

AU - Li, Jiahao

N1 - Publisher Copyright: © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

PY - 2024

Y1 - 2024

N2 - The technology of speech synthesis and conversion has made good progress with the development of deep learning. However, such technology can also do harm to information security and may be applied for illegal uses. Therefore, researchers have conducted a lot of research on the task of speech deep forgery detection recently. Corresponding to this, the Audio Deep Synthesis Detection Challenge 2023 (ADD 2023) is held. In this paper, we propose a fake audio detecting system using a pre-trained model, focusing on partially fake audio detection tasks. We have presented our models to the ADD 2023 challenge. In the final competition, our system got a score of 0.4855 in the manipulation region location track.

AB - The technology of speech synthesis and conversion has made good progress with the development of deep learning. However, such technology can also do harm to information security and may be applied for illegal uses. Therefore, researchers have conducted a lot of research on the task of speech deep forgery detection recently. Corresponding to this, the Audio Deep Synthesis Detection Challenge 2023 (ADD 2023) is held. In this paper, we propose a fake audio detecting system using a pre-trained model, focusing on partially fake audio detection tasks. We have presented our models to the ADD 2023 challenge. In the final competition, our system got a score of 0.4855 in the manipulation region location track.

KW - audio deepfake detection

KW - deep-learning

KW - fake region location

KW - manipulation

UR - http://www.scopus.com/inward/record.url?scp=85186675762&partnerID=8YFLogxK

U2 - 10.1007/978-981-97-0601-3_30

DO - 10.1007/978-981-97-0601-3_30

M3 - Conference contribution

AN - SCOPUS:85186675762

SN - 9789819706006

T3 - Communications in Computer and Information Science

SP - 346

EP - 353

BT - Man-Machine Speech Communication - 18th National Conference, NCMMSC 2023, Proceedings

A2 - Jia, Jia

A2 - Ling, Zhenhua

A2 - Chen, Xie

A2 - Li, Ya

A2 - Zhang, Zixing

PB - Springer Science and Business Media Deutschland GmbH

T2 - 18th National Conference on Man-Machine Speech Communication, NCMMSC 2023

Y2 - 8 December 2023 through 11 December 2023

ER -

Zhang J, Liu H, Deng M, Wang J, Sun Y, Xu L et al. An Improved System for Partially Fake Audio Detection Using Pre-trained Model. In Jia J, Ling Z, Chen X, Li Y, Zhang Z, editors, Man-Machine Speech Communication - 18th National Conference, NCMMSC 2023, Proceedings. Springer Science and Business Media Deutschland GmbH. 2024. p. 346-353. (Communications in Computer and Information Science). doi: 10.1007/978-981-97-0601-3_30