DP-VOXLET: Provable Speaker Anonymization for Disentangled Speech Representations

arXiv:2608.30969 · cs.CR · Submitted 2026-08-31 · Read on arXiv

cs.CR

Submitted: 2026-08-31

Updated: 2026-08-31

Journal ref: Published at Interspeech 2026

Code: https://github.com/uvm-plaid/dpvc

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Differential Privacy — 36× in this paper · explained in 4 episodes
• Benchmark — 10× in this paper · explained in 2 episodes
• Equal Error Rate — 7× in this paper
• Embeddings — 6× in this paper · explained in 2 episodes
• Verification — 5× in this paper · explained in 2 episodes
• Differentially Private — 4× in this paper · explained in 3 episodes
• Latent Representation — 4× in this paper · explained in 2 episodes
• Word Error Rate — 3× in this paper
• Accuracy — 1× in this paper · explained in 1 episode
• Adam — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Differential Privacy (DP) — 1× in this paper · explained in 7 episodes
• Diffusion Model — 1× in this paper · explained in 8 episodes
• Diffusion Models — 1× in this paper · explained in 6 episodes
• Intelligence Advanced Research Projects Activity — 1× in this paper
• Latent Space — 1× in this paper · explained in 7 episodes
• Regularization — 1× in this paper · explained in 3 episodes
• Variational Autoencoder (VAE) — 1× in this paper · explained in 3 episodes

Sources

• Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques
• Are disentangled representations all you need to build speaker anonymization systems?
• ControlVC: Zero-Shot Voice Conversion with Time-Varying Controls on Pitch and Speed
• Speaker anonymisation using the McAdams coefficient
• VoiceMask: Anonymize and Sanitize Voice Input on Mobile Devices
• OpenVoice: Versatile Instant Voice Cloning
• Design Choices for X-vector Based Speaker Anonymization
• The VoicePrivacy 2024 Challenge Evaluation Plan
• Speaker Anonymization Using X-vector and Neural Waveform Models
• vec2wav 2.0: Advancing Voice Conversion via Discrete Token Vocoders
• NaturalSpeech 3: Zero-Shot Speech Synthesis with Factorized Codec and Diffusion Models
• Auto-Encoding Variational Bayes

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills
• Token Composition: A Graph Based on EVM Logs