PSVRF: Learning to restore Pitch-Shifted Voice without reference
This addresses a security vulnerability in speaker verification systems against pitch-scaling attacks, offering a more practical solution than existing methods that require reference voices.
The paper tackles the problem of restoring pitch-shifted voices to enhance security in Automatic Speaker Verification systems, proposing a no-reference method called PSVRF that outperforms state-of-the-art reference-based approaches on datasets like AISHELL-1 and AISHELL-3.
Pitch scaling algorithms have a significant impact on the security of Automatic Speaker Verification (ASV) systems. Although numerous anti-spoofing algorithms have been proposed to identify the pitch-shifted voice and even restore it to the original version, they either have poor performance or require the original voice as a reference, limiting the prospects of applications. In this paper, we propose a no-reference approach termed PSVRF$^1$ for high-quality restoration of pitch-shifted voice. Experiments on AISHELL-1 and AISHELL-3 demonstrate that PSVRF can restore the voice disguised by various pitch-scaling techniques, which obviously enhances the robustness of ASV systems to pitch-scaling attacks. Furthermore, the performance of PSVRF even surpasses that of the state-of-the-art reference-based approach.