Shift to Your Device: Data Augmentation for Device-Independent Speaker Verification Anti-Spoofing
Published in Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP), 2023
Recommended citation: Junhao Wang, Li Lu*, Zhongjie Ba, Feng Lin, Kui Ren. "Shift to Your Device: Data Augmentation for Device-Independent Speaker Verification Anti-Spoofing." Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (IEEE ICASSP). Rhodes Island, Greece. 2023. doi: 10.1109/ICASSP49357.2023.10097168.
IEEE International Conference on Acoustics, Speech and Signal Processing is the flagship journal of IEEE Signal Processing Society. IEEE ICASSP is a CCF-B conference.
Abstract: This paper proposes a novel Deconvolution-enhanced data Augmentation method, DeAug, for ultrasonic-based speaker verification anti-spoofing systems to detect the liveness of voice sources in physical access, which aims to improve the performance of liveness detection on unseen devices where no data is collected yet. Specifically, DeAug first employs a wiener deconvolution pre-processing on available collected data to generate enhanced clean signal samples. Then, the generated samples are convolved with different device impulse responses, to enable the signal with the unseen devices’ channel characteristics.