Enhancing speech privacy with slicing - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2022

Enhancing speech privacy with slicing

Abstract

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.
Fichier principal
Vignette du fichier
maouche_IS2022.pdf (322.81 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03369137 , version 1 (07-10-2021)
hal-03369137 , version 2 (01-07-2022)

Identifiers

  • HAL Id : hal-03369137 , version 2

Cite

Mohamed Maouche, Brij Mohan Lal Srivastava, Nathalie Vauquier, Aurélien Bellet, Marc Tommasi, et al.. Enhancing speech privacy with slicing. Interspeech 2022 - Human and Humanizing Speech Technology, Sep 2022, Incheon, South Korea. ⟨hal-03369137v2⟩
247 View
424 Download

Share

Gmail Mastodon Facebook X LinkedIn More