Partially Fake Audio Detection by Self-Attention-Based Fake Span Discovery

• Published in: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) pp. 9236 - 9240
• Main Authors: Wu, Haibin, Kuo, Heng-Cheng, Zheng, Naijun, Hung, Kuo-Hsuan, Lee, Hung-Yi, Tsao, Yu, Wang, Hsin-Min, Meng, Helen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.01.2022
• Subjects: Acoustics; Anti-spoofing; audio deep synthesis detection challenge; Biological system modeling; Biometrics (access control); Conferences; partially fake audio detection; Predictive models; Robustness; Signal processing

The past few years have witnessed the significant advances of speech synthesis and voice conversion technologies. However, such technologies can undermine the robustness of broadly implemented biometric identification models and can be harnessed by in-the-wild attackers for illegal uses. The ASVspoo...