Graduate School and Research Center in Digital Sciences

Introducing the VoicePrivacy initiative

Tomashenko, Natalia; Lal Srivastava, Brij Mohan; Wang, Xin; Vincent, Emmanuel; Nautsch, Andreas; Yamagishi, Junichi; Evans, Nicholas; Patino, Jose; Bonastre, J.-F; Noé, Paul-Gauthier; Todisco, Massimiliano

INTERSPEECH 2020, 21st Annual Conference of the International Speech Communication Association, 25-29 October 2020, Shanghai, China

The VoicePrivacy initiative aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges. In this paper, we formulate the voice anonymization task selected for the VoicePrivacy 2020 Challenge and describe the datasets used for system development and evaluation. We also present the attack models and the associated objective and subjective evaluation metrics. We introduce two anonymization baselines and report objective evaluation results.    

Document Arxiv Hal Bibtex

Title:Introducing the VoicePrivacy initiative
Type:Conference
Language:English
City:Shanghai
Country:CHINA
Date:
Department:Digital Security
Eurecom ref:6252
Copyright: © ISCA. Personal use of this material is permitted. The definitive version of this paper was published in INTERSPEECH 2020, 21st Annual Conference of the International Speech Communication Association, 25-29 October 2020, Shanghai, China and is available at :
Bibtex: @inproceedings{EURECOM+6252, year = {2020}, title = {{I}ntroducing the {V}oice{P}rivacy initiative}, author = {{T}omashenko, {N}atalia and {L}al {S}rivastava, {B}rij {M}ohan and {W}ang, {X}in and {V}incent, {E}mmanuel and {N}autsch, {A}ndreas and {Y}amagishi, {J}unichi and {E}vans, {N}icholas and {P}atino, {J}ose and {B}onastre, {J}.-{F} and {N}o{\'e}, {P}aul-{G}authier and {T}odisco, {M}assimiliano}, booktitle = {{INTERSPEECH} 2020, 21st {A}nnual {C}onference of the {I}nternational {S}peech {C}ommunication {A}ssociation, 25-29 {O}ctober 2020, {S}hanghai, {C}hina}, address = {{S}hanghai, {CHINA}}, month = {05}, url = {http://www.eurecom.fr/publication/6252} }
See also: