Speaker Anonymisation Using the McAdams Coefficient - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Speaker Anonymisation Using the McAdams Coefficient

Natalia Tomashenko
Massimiliano Todisco
  • Fonction : Auteur
  • PersonId : 1199117
Andreas Nautsch
Nicholas Evans
  • Fonction : Auteur
  • PersonId : 938450

Résumé

Anonymisation has the goal of manipulating speech signals in order to degrade the reliability of automatic approaches to speaker recognition, while preserving other aspects of speech, such as those relating to intelligibility and naturalness. This paper reports an approach to anonymisation that, unlike other current approaches, requires no training data, is based upon well-known signal processing techniques and is both efficient and effective. The proposed solution uses the McAdams coefficient to transform the spectral envelope of speech signals. Results derived using common VoicePrivacy 2020 databases and protocols show that random, optimised transformations can outperform competing solutions in terms of anonymisation while causing only modest, additional degradations to intelligibility, even in the case of a semi-informed privacy adversary.

Dates et versions

hal-03346206 , version 1 (16-09-2021)

Identifiants

Citer

Jose Patino, Natalia Tomashenko, Massimiliano Todisco, Andreas Nautsch, Nicholas Evans. Speaker Anonymisation Using the McAdams Coefficient. Interspeech 2021, Aug 2021, Brno, Czech Republic. pp.1099-1103, ⟨10.21437/Interspeech.2021-1070⟩. ⟨hal-03346206⟩
39 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More