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

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

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.

源语言英语
主期刊名Man-Machine Speech Communication - 18th National Conference, NCMMSC 2023, Proceedings
编辑Jia Jia, Zhenhua Ling, Xie Chen, Ya Li, Zixing Zhang
出版商Springer Science and Business Media Deutschland GmbH
346-353
页数8
ISBN(印刷版)9789819706006
DOI
出版状态已出版 - 2024
活动18th National Conference on Man-Machine Speech Communication, NCMMSC 2023 - Suzhou, 中国
期限: 8 12月 202311 12月 2023

出版系列

姓名Communications in Computer and Information Science
2006
ISSN(印刷版)1865-0929
ISSN(电子版)1865-0937

会议

会议18th National Conference on Man-Machine Speech Communication, NCMMSC 2023
国家/地区中国
Suzhou
时期8/12/2311/12/23

指纹

探究 'An Improved System for Partially Fake Audio Detection Using Pre-trained Model' 的科研主题。它们共同构成独一无二的指纹。

引用此