Ecole d'ingénieur et centre de recherche en Sciences du numérique

Speaker anonymisation using the McAdams coefficient

Patino, Jose; Todisco, Massimiliano; Nautsch, Andreas; Evans, Nicholas

Research Report RR-20-343, 28 February 2020

This report presents an alternative to speaker anonymisation that does not require external training data and is based on a single processing block using basic signal processing techniques. The proposed method employs the McAdams coefficient to apply a slight contraction/expansion to the poles derived from linear predictive coding (LPC) coefficients of speech content on a frame-by-frame basis, consequently leading to a transformation of the related formants.

Document Bibtex

Titre:Speaker anonymisation using the McAdams coefficient
Mots Clés:Speaker anonymisation, privacy preservation, signal processing, speaker recognition
Type:Rapport
Langue:English
Ville:
Date:
Département:Sécurité numérique
Eurecom ref:6190
Copyright: © EURECOM. Personal use of this material is permitted. The definitive version of this paper was published in Research Report RR-20-343, 28 February 2020 and is available at :
Bibtex: @techreport{EURECOM+6190, year = {2020}, title = {{S}peaker anonymisation using the {M}c{A}dams coefficient}, author = {{P}atino, {J}ose and {T}odisco, {M}assimiliano and {N}autsch, {A}ndreas and {E}vans, {N}icholas}, number = {EURECOM+6190}, month = {02}, institution = {Eurecom}, url = {http://www.eurecom.fr/publication/6190},, }
Voir aussi: