Speech Pseudonymisation Assessment Using Voice Similarity Matrices - Archive ouverte HAL Access content directly
Conference Papers Year :

Speech Pseudonymisation Assessment Using Voice Similarity Matrices

Driss Matrouf
Natalia Tomashenko
Andreas Nautsch
Nicholas Evans
  • Function : Author
  • PersonId : 938450

Abstract

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.
Fichier principal
Vignette du fichier
speech_pseudonymisation_assessment_using_voice_similarity_matrices.pdf (378.72 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02925559 , version 1 (30-08-2020)

Identifiers

  • HAL Id : hal-02925559 , version 1

Cite

Paul-Gauthier Noé, Jean-François Bonastre, Driss Matrouf, Natalia Tomashenko, Andreas Nautsch, et al.. Speech Pseudonymisation Assessment Using Voice Similarity Matrices. Interspeech 2020, Oct 2020, Shanghai, China. ⟨hal-02925559⟩
170 View
76 Download

Share

Gmail Facebook Twitter LinkedIn More