The VoicePrivacy 2020 Challenge: Results ...
Type de document :
Pré-publication ou Document de travail
URL permanente :
Titre :
The VoicePrivacy 2020 Challenge: Results and findings
Auteur(s) :
Tomashenko, Natalia [Auteur]
Laboratoire Informatique d'Avignon [LIA]
Wang, Xin [Auteur]
National Institute of Informatics [NII]
Vincent, Emmanuel [Auteur]
Laboratoire Lorrain de Recherche en Informatique et ses Applications [LORIA]
Patino, Jose [Auteur]
Eurecom [Sophia Antipolis]
Srivastava, Brij Mohan Lal [Auteur]
Machine Learning in Information Networks [MAGNET]
Speech Modeling for Facilitating Oral-Based Communication [MULTISPEECH]
Noé, Paul-Gauthier [Auteur]
Laboratoire Informatique d'Avignon [LIA]
Nautsch, Andreas [Auteur]
Eurecom [Sophia Antipolis]
Evans, Nicholas [Auteur]
Eurecom [Sophia Antipolis]
Yamagishi, Junichi [Auteur]
National Institute of Informatics [NII]
University of Edinburgh [Edin.]
O'brien, Benjamin [Auteur]
Laboratoire Parole et Langage [LPL]
Chanclu, Anaïs [Auteur]
Laboratoire Informatique d'Avignon [LIA]
Bonastre, Jean-François [Auteur]
Laboratoire Informatique d'Avignon [LIA]
Todisco, Massimiliano [Auteur]
Eurecom [Sophia Antipolis]
Maouche, Mohamed [Auteur]
Machine Learning in Information Networks [MAGNET]
Laboratoire Informatique d'Avignon [LIA]
Wang, Xin [Auteur]
National Institute of Informatics [NII]
Vincent, Emmanuel [Auteur]
Laboratoire Lorrain de Recherche en Informatique et ses Applications [LORIA]
Patino, Jose [Auteur]
Eurecom [Sophia Antipolis]
Srivastava, Brij Mohan Lal [Auteur]
Machine Learning in Information Networks [MAGNET]
Speech Modeling for Facilitating Oral-Based Communication [MULTISPEECH]
Noé, Paul-Gauthier [Auteur]
Laboratoire Informatique d'Avignon [LIA]
Nautsch, Andreas [Auteur]
Eurecom [Sophia Antipolis]
Evans, Nicholas [Auteur]
Eurecom [Sophia Antipolis]
Yamagishi, Junichi [Auteur]
National Institute of Informatics [NII]
University of Edinburgh [Edin.]
O'brien, Benjamin [Auteur]
Laboratoire Parole et Langage [LPL]
Chanclu, Anaïs [Auteur]
Laboratoire Informatique d'Avignon [LIA]
Bonastre, Jean-François [Auteur]
Laboratoire Informatique d'Avignon [LIA]
Todisco, Massimiliano [Auteur]
Eurecom [Sophia Antipolis]
Maouche, Mohamed [Auteur]
Machine Learning in Information Networks [MAGNET]
Mot(s)-clé(s) en anglais :
automatic speech recognition
attack model
metrics
utility
privacy
anonymization
speech synthesis
voice conversion
speaker verification
attack model
metrics
utility
privacy
anonymization
speech synthesis
voice conversion
speaker verification
Discipline(s) HAL :
Informatique [cs]/Intelligence artificielle [cs.AI]
Résumé en anglais : [en]
This paper presents the results and analyses stemming from the first VoicePrivacy 2020 Challenge which focuses on developing anonymization solutions for speech technology. We provide a systematic overview of the challenge ...
Lire la suite >This paper presents the results and analyses stemming from the first VoicePrivacy 2020 Challenge which focuses on developing anonymization solutions for speech technology. We provide a systematic overview of the challenge design with an analysis of submitted systems and evaluation results. In particular, we describe the voice anonymization task and datasets used for system development and evaluation. Also, we present different attack models and the associated objective and subjective evaluation metrics. We introduce two anonymization baselines and provide a summary description of the anonymization systems developed by the challenge participants. We report objective and subjective evaluation results for baseline and submitted systems. In addition, we present experimental results for alternative privacy metrics and attack models developed as a part of the post-evaluation analysis. Finally, we summarise our insights and observations that will influence the design of the next VoicePrivacy challenge edition and some directions for future voice anonymization research.Lire moins >
Lire la suite >This paper presents the results and analyses stemming from the first VoicePrivacy 2020 Challenge which focuses on developing anonymization solutions for speech technology. We provide a systematic overview of the challenge design with an analysis of submitted systems and evaluation results. In particular, we describe the voice anonymization task and datasets used for system development and evaluation. Also, we present different attack models and the associated objective and subjective evaluation metrics. We introduce two anonymization baselines and provide a summary description of the anonymization systems developed by the challenge participants. We report objective and subjective evaluation results for baseline and submitted systems. In addition, we present experimental results for alternative privacy metrics and attack models developed as a part of the post-evaluation analysis. Finally, we summarise our insights and observations that will influence the design of the next VoicePrivacy challenge edition and some directions for future voice anonymization research.Lire moins >
Langue :
Anglais
Projet ANR :
Collections :
Source :
Date de dépôt :
2021-11-21T02:00:58Z
Fichiers
- https://hal.archives-ouvertes.fr/hal-03332224v3/document
- Accès libre
- Accéder au document