Generating identities with mixture models for speaker anonymization. (March 2022)

• Record Type: Journal Article
• Authors: Turner, Henry; Lovisotto, Giulio; Martinovic, Ivan
• Is Part Of: Computer speech & language. Volume 72(2022)
• Publication Date: 2022-03
• Subjects: Speaker anonymization -- Speech -- Speaker -- Anonymization -- Privacy; Speech processing systems -- Periodicals; Automatic speech recognition -- Periodicals; Computers -- Periodicals; Linguistics -- Periodicals; Speech-Language Pathology -- Periodicals; Traitement automatique de la parole -- Périodiques; Reconnaissance automatique de la parole -- Périodiques; Automatic speech recognition; Speech processing systems; Electronic journals; Periodicals; 006.454
• DOI: 10.1016/j.csl.2021.101318
• Languages: English
• ISSNs: 0885-2308

Abstract

Abstract: 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. Highlights: We identify a weakness in existing speaker identity generation methods. We propose a new identity generation method based on sampling from mixture models. We show our method is not impacted by the weakness of existing methods. Our experiments show improved voice diversity and similar anonymization performance.