CASIA OpenIR  > 模式识别国家重点实验室  > 智能交互
Continual Learning for Fake Audio Detection
Ma Haoxin1,2; Yi Jiangyan1; Tao Jianhua1,2,3; Bai Ye1,2; Tian Zhengkun1,2; Wang Chenglong1
Conference NameINTERSPEECH 2021
Conference Date2021-9
Conference Place线上(捷克)

Fake audio attack becomes a major threat to the speaker verification system. Although current detection approaches have achieved promising results on dataset-specific scenarios, they encounter difficulties on unseen spoofing data. Fine-tuning and retraining from scratch have been applied to incorporate new data. However, fine-tuning leads to performance degradation on previous data. Retraining takes a lot of time and computation resources. Besides, previous data are unavailable due to privacy in some situations. To solve the above problems, this paper proposes detecting fake without forgetting, a continual-learningbased method, to make the model learn new spoofing attacks incrementally. A knowledge distillation loss is introduced to loss function to preserve the memory of original model. Supposing the distribution of genuine voice is consistent among different scenarios, an extra embedding similarity loss is used as another constraint to further do a positive sample alignment. Experiments are conducted on the ASVspoof2019 dataset. The results show that our proposed method outperforms fine-tuning by the relative reduction of average equal error rate up to 81.62%.

Keywordfake audio detection continual learning detecting fake without forgetting
Indexed ByEI
Document Type会议论文
Affiliation1.NLPR, Institute of Automation, Chinese Academy of Sciences, China
2.School of Artificial Intelligence, University of Chinese Academy of Sciences, China
3.CAS Center for Excellence in Brain Science and Intelligence Technology, China
First Author AffilicationChinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
Recommended Citation
GB/T 7714
Ma Haoxin,Yi Jiangyan,Tao Jianhua,et al. Continual Learning for Fake Audio Detection[C],2021.
Files in This Item: Download All
File Name/Size DocType Version Access License
连续学习ma21b_interspeec(2113KB)会议论文 开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Ma Haoxin]'s Articles
[Yi Jiangyan]'s Articles
[Tao Jianhua]'s Articles
Baidu academic
Similar articles in Baidu academic
[Ma Haoxin]'s Articles
[Yi Jiangyan]'s Articles
[Tao Jianhua]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Ma Haoxin]'s Articles
[Yi Jiangyan]'s Articles
[Tao Jianhua]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 连续学习ma21b_interspeech.pdf
Format: Adobe PDF
All comments (0)
No comment.

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.