DiffAnon: Diffusion-based Prosody Control for Voice Anonymization

[2604.26281] DiffAnon: Diffusion-based Prosody Control for Voice Anonymization Skip to main content Search Submit Donate Log in Electrical Engineering and Systems Science > Audio and Speech Processing arXiv:2604.26281 (eess) [Submitted on 29 Apr 2026 ( v1 ), last revised 28 Aug 2026 (this version, v2)] Title: DiffAnon: Diffusion-based Prosody Control for Voice Anonymization Authors: Ismail Rasim Ulgen , Zexin Cai , Nicholas Andrews , Philipp Koehn , Berrak Sisman View PDF HTML (experimental) Abstract: To preserve or not to preserve prosody is a central question in voice anonymization. Prosody conveys meaning and affect, yet is tightly coupled with speaker identity. Existing methods either discard prosody for privacy or lack a principled mechanism to control the utility-privacy trade-off, operating at fixed design points. We propose DiffAnon, a diffusion-based anonymization method with classifier-free guidance (CFG) that provides explicit, continuous inference-time control over prosody preservation. DiffAnon refines acoustic detail over semantic embeddings of an RVQ codec, enabling smooth interpolation between anonymization strength and prosodic fidelity within a single model. To the best of our knowledge, it is the first voice anonymization framework to provide structured, interpolatable inference-time prosody control. Experiments demonstrate structured trade-off behavior, achieving strong utility while maintaining competitive privacy across controllable operating points. Comments: Accepted to Interspeech 2026 Subjects: Audio and Speech Processing (eess.AS) ; Machine Learning (cs.LG); Sound (cs.SD) Cite as: arXiv:2604.26281 [eess.AS] (or arXiv:2604.26281v2 [eess.AS] for this version) https://doi.org/10.48550/arXiv.2604.26281 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ismail Rasim Ulgen [ view email ] [v1] Wed, 29 Apr 2026 04:22:59 UTC (887 KB) [v2] Fri, 28 Aug 2026 02:58:12 UTC (888 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Current browse context: eess.AS < prev | next > new | recent | 2026-04 Change to browse by: cs cs.LG cs.SD eess References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from (opens in new tab) (opens in new tab) (opens in new tab)

Related documents

• DiffAnon: Diffusion-based Prosody Control for Voice Anonymization#682664
• A Large-Scale Per-Speaker Analysis of Re-identification Risk in Speech Anonymization#266114
• Anonymization, Not Elimination: Utility-Preserved Speech Anonymization#925137
• Anonymization, Not Elimination: Utility-Preserved Speech Anonymization#920903
• DP-VOXLET: Provable Speaker Anonymization for Disentangled Speech Representations#622430