Metraipolis › archive › dc_248591c558d5
Anonymization, Not Elimination: Utility-Preserved Speech Anonymization — arXiv:2604.17000
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2604.17000
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T01:11:38.731Z
- SHA-256 of the archived text
76d8858565fde48b99fe737d993cc7003f890745e4b382e4b2b28fe83610b69e- Stable URL of this page
https://metraipolis.com/documento/dc_248591c558d5
How to cite
Anonymization, Not Elimination: Utility-Preserved Speech Anonymization — arXiv:2604.17000 — arXiv (en), https://arxiv.org/abs/2604.17000 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_248591c558d5 (Metraipolis archive dc_248591c558d5, sha256 76d8858565fde48b99fe737d993cc7003f890745e4b382e4b2b28fe83610b69e)
BibTeX
@misc{dc248591c558d5,
title = {Anonymization, Not Elimination: Utility-Preserved Speech Anonymization — arXiv:2604.17000},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2604.17000},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_248591c558d5; sha256 76d8858565fde48b99fe737d993cc7003f890745e4b382e4b2b28fe83610b69e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2604.17000. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
The growing reliance on large-scale speech data has made privacy protection a critical concern. However, existing anonymization approaches often degrade data utility, for example by disrupting acoustic continuity or reducing vocal diversity, which compromises the value of speech data for downstream tasks such as Automatic Speech Recognition (ASR), Text-to-Speech (TTS), and Speech Emotion Recognition (SER). Current evaluation practices are also limited, as they mainly rely on direct testing of anonymized speech with pretrained models, providing only a partial view of utility. To address these issues, we propose a novel two-stage framework that protects both linguistic content and acoustic identity while maintaining usability. For content privacy, we employ a generative speech editing model to seamlessly replace personally identifiable information (PII), and for voice privacy, we introduce F3-VA, a flow-matching-based anonymization framework with a three-stage design that produces diverse and distinct anonymized speakers. To enable a more comprehensive assessment, we evaluate privacy using both acoustic- and content-based speaker verification metrics, and assess utility by training ASR, TTS, and SER models from scratch. Experimental results show that our framework achieves stronger privacy protection with minimal utility degradation compared to baselines from the VoicePrivacy Challenge, while the proposed evaluation protocol provides a more realistic reflection of the utility of anonymized speech under privacy protection. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-04 in cs.AI). Categorie arXiv: Audio and Speech Processing (eess.AS) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2604.17000 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T00:28:02.923Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-04?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).