Voice spoofing detector: A unified anti-spoofing framework

作者：

Highlights：

• Novel ATCoP feature descriptor for voice presentation attack detection.

• Unified voice anti-spoofing method to detect the single- and multi-order attacks.

• Accurate voice spoofing detection in compressed and uncompressed audios.

• Our method performs remarkably well for audio deepfakes detection.

摘要

•Novel ATCoP feature descriptor for voice presentation attack detection.•Unified voice anti-spoofing method to detect the single- and multi-order attacks.•Accurate voice spoofing detection in compressed and uncompressed audios.•Our method performs remarkably well for audio deepfakes detection.

论文关键词：Acoustic ternary co-occurrence patterns,AI for multimedia security,AI for voice-based biometrics in IoT,Anti-spoofing against multiple attack vectors,Deepfakes,Voice spoofing detection

论文评审过程：Received 15 August 2021, Revised 4 January 2022, Accepted 25 February 2022, Available online 9 March 2022, Version of Record 11 March 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.116770