Speech Pseudonymisation Assessment Using Voice Similarity Matrices
This addresses privacy concerns in speech technologies for users and developers, but is incremental as it builds on existing anonymisation efforts.
The paper tackled the lack of metrics for assessing speech pseudonymisation, which aims to mask speaker identity while preserving voice distinctiveness, by proposing the first visualisation and two novel objective metrics based on voice similarity matrices.
The proliferation of speech technologies and rising privacy legislation calls for the development of privacy preservation solutions for speech applications. These are essential since speech signals convey a wealth of rich, personal and potentially sensitive information. Anonymisation, the focus of the recent VoicePrivacy initiative, is one strategy to protect speaker identity information. Pseudonymisation solutions aim not only to mask the speaker identity and preserve the linguistic content, quality and naturalness, as is the goal of anonymisation, but also to preserve voice distinctiveness. Existing metrics for the assessment of anonymisation are ill-suited and those for the assessment of pseudonymisation are completely lacking. Based upon voice similarity matrices, this paper proposes the first intuitive visualisation of pseudonymisation performance for speech signals and two novel metrics for objective assessment. They reflect the two, key pseudonymisation requirements of de-identification and voice distinctiveness.