Graduate School and Research Center in Digital Sciences

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

Title:Speaker anonymisation using the McAdams coefficient
Keywords:Speaker anonymisation, privacy preservation, signal processing, speaker recognition
Department:Digital Security
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 = {},, }
See also: