DiffAnon: Diffusion-based Prosody Control for Voice Anonymization
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909000114634752 |
|---|---|
| author | Ulgen, Ismail Rasim Cai, Zexin Andrews, Nicholas Koehn, Philipp Sisman, Berrak |
| author_facet | Ulgen, Ismail Rasim Cai, Zexin Andrews, Nicholas Koehn, Philipp Sisman, Berrak |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_26281 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | DiffAnon: Diffusion-based Prosody Control for Voice Anonymization Ulgen, Ismail Rasim Cai, Zexin Andrews, Nicholas Koehn, Philipp Sisman, Berrak Audio and Speech Processing Machine Learning Sound 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. |
| title | DiffAnon: Diffusion-based Prosody Control for Voice Anonymization |
| topic | Audio and Speech Processing Machine Learning Sound |
| url | https://arxiv.org/abs/2604.26281 |