Generating identities with mixture models for speaker anonymization

Journal article

Speaker anonymization methods are a growing research area, due to the common use of voice interfaces coupled with growing privacy requirements. However, existing systems suffer from several issues, in particular a reduction in the entropy space of the newly created voices. This is problematic as it reduces the diversity of the produced anonymous voices, thus making distinguishing between anonymized voices more difficult, and limiting the number of anonymous voices that can be generated. In this work we propose a method for creating the new identity component for anonymized voices, termed an x-vector, which aims to better reflect the natural diversity of voices, in turn increasing the diversity of the voices of anonymized speakers. We combine this identity generation method with existing anonymization schemes, to produce an overall anonymization system, which we evaluate. Our results demonstrate that our scheme creates more diverse anonymized voices than the existing baseline method. Furthermore, our results show that the assumption of perfect de-coupling between identity and non-identity voice components used in existing speaker anonymization frameworks does not hold, highlighting a clear avenue for future work.

Authors: Turner, H; Lovisotto, G; Martinovic, I

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: Elsevier
• Journal: Computer Speech and Language
• Volume: 72
• Article number: 101318
• Publication date: 2021-11-13
• Acceptance date: 2021-10-25
• DOI: 10.1016/j.csl.2021.101318
• ISSN: 0885-2308
• Language: English
• Keywords: FFR