Analysis of Speech Temporal Dynamics in the Context of Speaker Verification and Voice Anonymization

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tomashenko, Natalia, Vincent, Emmanuel, Tommasi, Marc
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917997871890432
author Tomashenko, Natalia
Vincent, Emmanuel
Tommasi, Marc
author_facet Tomashenko, Natalia
Vincent, Emmanuel
Tommasi, Marc
contents In this paper, we investigate the impact of speech temporal dynamics in application to automatic speaker verification and speaker voice anonymization tasks. We propose several metrics to perform automatic speaker verification based only on phoneme durations. Experimental results demonstrate that phoneme durations leak some speaker information and can reveal speaker identity from both original and anonymized speech. Thus, this work emphasizes the importance of taking into account the speaker's speech rate and, more importantly, the speaker's phonetic duration characteristics, as well as the need to modify them in order to develop anonymization systems with strong privacy protection capacity.
format Preprint
id arxiv_https___arxiv_org_abs_2412_17164
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Analysis of Speech Temporal Dynamics in the Context of Speaker Verification and Voice Anonymization
Tomashenko, Natalia
Vincent, Emmanuel
Tommasi, Marc
Audio and Speech Processing
Computation and Language
Sound
In this paper, we investigate the impact of speech temporal dynamics in application to automatic speaker verification and speaker voice anonymization tasks. We propose several metrics to perform automatic speaker verification based only on phoneme durations. Experimental results demonstrate that phoneme durations leak some speaker information and can reveal speaker identity from both original and anonymized speech. Thus, this work emphasizes the importance of taking into account the speaker's speech rate and, more importantly, the speaker's phonetic duration characteristics, as well as the need to modify them in order to develop anonymization systems with strong privacy protection capacity.
title Analysis of Speech Temporal Dynamics in the Context of Speaker Verification and Voice Anonymization
topic Audio and Speech Processing
Computation and Language
Sound
url https://arxiv.org/abs/2412.17164