Improving Security in McAdams Coefficient-Based Speaker Anonymization by Watermarking Method
This work addresses privacy protection in speech processing for applications like voice assistants, but it is incremental as it builds on existing McAdams coefficient-based anonymization.
The paper tackled the problem of enhancing security in speaker anonymization using McAdams coefficients by proposing a watermarking method that embeds binary bits via coefficient switching and detects them through power spectrum comparison. The result showed that the method met watermarking requirements for blind detection, inaudibility, and robustness, and significantly improved anonymization performance compared to a baseline system in the VoicePrivacy 2020 Challenge.
Speaker anonymization aims to suppress speaker individuality to protect privacy in speech while preserving the other aspects, such as speech content. One effective solution for anonymization is to modify the McAdams coefficient. In this work, we propose a method to improve the security for speaker anonymization based on the McAdams coefficient by using a speech watermarking approach. The proposed method consists of two main processes: one for embedding and one for detection. In embedding process, two different McAdams coefficients represent binary bits ``0" and ``1". The watermarked speech is then obtained by frame-by-frame bit inverse switching. Subsequently, the detection process is carried out by a power spectrum comparison. We conducted objective evaluations with reference to the VoicePrivacy 2020 Challenge (VP2020) and of the speech watermarking with reference to the Information Hiding Challenge (IHC) and found that our method could satisfy the blind detection, inaudibility, and robustness requirements in watermarking. It also significantly improved the anonymization performance in comparison to the secondary baseline system in VP2020.