Titre :

Enhancing speech privacy with slicing

Auteur(s) :

Maouche, Mohamed [Auteur]
Machine Learning in Information Networks [MAGNET]
Srivastava, Brij Mohan Lal [Auteur]
Speech Modeling for Facilitating Oral-Based Communication [MULTISPEECH]
Machine Learning in Information Networks [MAGNET]
Vauquier, Nathalie [Auteur]
Machine Learning in Information Networks [MAGNET]
Bellet, Aurelien [Auteur]
Machine Learning in Information Networks [MAGNET]
Tommasi, Marc [Auteur]
Machine Learning in Information Networks [MAGNET]
Vincent, Emmanuel [Auteur]
Speech Modeling for Facilitating Oral-Based Communication [MULTISPEECH]

Titre de la manifestation scientifique :

Interspeech 2022 - Human and Humanizing Speech Technology

Ville :

Incheon

Pays :

Corée du Sud

Date de début de la manifestation scientifique :

2022-09-18

Mot(s)-clé(s) en anglais :

anonymization
speaker verification
automatic speech recognition
privacy
segmentation

Discipline(s) HAL :

Informatique [cs]/Cryptographie et sécurité [cs.CR]
Informatique [cs]/Informatique et langage [cs.CL]
Informatique [cs]/Apprentissage [cs.LG]

Résumé en anglais : [en]

Privacy preservation calls for speech anonymization methods which hide the speaker's identity while minimizing the impact on downstream tasks such as automatic speech recognition (ASR) training or decoding. In the recent ...
Lire la suite >Privacy preservation calls for speech anonymization methods which hide the speaker's identity while minimizing the impact on downstream tasks such as automatic speech recognition (ASR) training or decoding. In the recent VoicePrivacy 2020 Challenge, several anonymization methods have been proposed to transform speech utterances in a way that preserves their verbal and prosodic contents while reducing the accuracy of a speaker verification system. In this paper, we propose to further increase the privacy achieved by such methods by segmenting the utterances into shorter slices. We show that our approach has two major impacts on privacy. First, it reduces the accuracy of speaker verification with respect to unsegmented utterances. Second, it also reduces the amount of personal information that can be extracted from the verbal content, in a way that cannot easily be reversed by an attacker. We also show that it is possible to train an ASR system from anonymized speech slices with negligible impact on the word error rate.Lire moins >

Langue :

Anglais

Comité de lecture :

Oui

Audience :

Internationale

Vulgarisation :

Non

Projet ANR :

Apprentissage distribué, personnalisé, préservant la privacité pour le traitement de la parole

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL