In this section
@inproceedings{Nespoli:2023:10.21437/Interspeech.2023-1341,
author = {Nespoli, F and Barreda, D and Bitzer, J and Naylor, PA},
doi = {10.21437/Interspeech.2023-1341},
pages = {3854--3858},
title = {Two-Stage Voice Anonymization for Enhanced Privacy},
url = {http://dx.doi.org/10.21437/Interspeech.2023-1341},
year = {2023}
}
TY - CPAPER
AB - In recent years, the need for privacy preservation when manipulating or storing personal data, including speech, has become a major issue. In this paper, we present a system addressing the speaker-level anonymization problem. We propose and evaluate a two-stage anonymization pipeline exploiting a state-of-the-art anonymization model described in the Voice Privacy Challenge 2022 in combination with a zero-shot voice conversion architecture able to capture speaker characteristics from a few seconds of speech. We show this architecture can lead to strong privacy preservation while preserving pitch information. Finally, we propose a new compressed metric to evaluate anonymization systems in privacy scenarios with different constraints on privacy and utility.
AU - Nespoli,F
AU - Barreda,D
AU - Bitzer,J
AU - Naylor,PA
DO - 10.21437/Interspeech.2023-1341
EP - 3858
PY - 2023///
SN - 2308-457X
SP - 3854
TI - Two-Stage Voice Anonymization for Enhanced Privacy
UR - http://dx.doi.org/10.21437/Interspeech.2023-1341
ER -
Speech and Audio Processing Lab
CSP Group, EEE Department
Imperial College London
Exhibition Road, London, SW7 2AZ, United Kingdom