mlsanityData to 14 Oct 2026

Are disentangled representations all you need to build speaker anonymization systems?

arXiv 2208.10497 ↗First posted 22 Aug 2022cs.SD cs.AI cs.CRcited by 10

Not on the map. Why?

Abstract (arXiv)

Speech signals contain a lot of sensitive information, such as the speaker's identity, which raises privacy concerns when speech data get collected. Speaker anonymization aims to transform a speech signal to remove the source speaker's identity while leaving the spoken content unchanged. Current methods perform the transformation by relying on content/speaker disentanglement and voice conversion. Usually, an acoustic model from an automatic speech recognition system extracts the content representation while an x-vector system extracts the speaker representation. Prior work has shown that the extracted features are not perfectly disentangled. This paper tackles how to improve features disentanglement, and thus the converted anonymized speech. We propose enhancing the disentanglement by removing speaker information from the acoustic model using vector quantization. Evaluation done using the VoicePrivacy 2022 toolkit showed that vector quantization helps conceal the original speaker identity while maintaining utility for speech recognition.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 22 of its 37 references that are in the map. First posted on arXiv 22 Aug 2022.

Builds on

22 of 37 references.

References · 22

  1. 2017Neural Discrete Representation Learningcited by 4,712
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2013Estimating or Propagating Gradients Through Stochastic Neurons for Conditional Computationcited by 2,079
  4. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  5. 2021VoxPopuli: A Large-Scale Multilingual Speech Corpus for Representation Learning, Semi-Supervised Learning and Interpretationcited by 463
  6. 2021Speech Resynthesis from Discrete Disentangled Self-Supervised Representationscited by 243
  7. 2018Fast Decoding in Sequence Models using Discrete Latent Variablescited by 104
  8. 2019Unsupervised speech representation learning using WaveNet autoencoderscited by 90
  9. 2020Introducing the VoicePrivacy Initiativecited by 49
  10. 2019Neural source-filter waveform models for statistical parametric speech synthesiscited by 46
  11. 2019Speaker Anonymization Using X-vector and Neural Waveform Modelscited by 41
  12. 2020F0-consistent many-to-many non-parallel voice conversion via conditional autoencodercited by 35
10 more
  1. 2019The GDPR & Speech Data: Reflections of Legal and Technology Communities, First Steps towards a Common Understandingcited by 19
  2. 2019Probing the Information Encoded in X-vectorscited by 18
  3. 2022Differentially Private Speaker Anonymizationcited by 16
  4. 2022Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Modelscited by 14
  5. 2018To Reverse the Gradient or Not: An Empirical Comparison of Adversarial and Multi-task Learning in Speech Recognitioncited by 10
  6. 2021A Study of F0 Modification for X-Vector Based Speech Pseudonymization Across Gendercited by 9
  7. 2021Comparing CTC and LFMMI for out-of-domain adaptation of wav2vec 2.0 acoustic modelcited by 6
  8. 2022The VoicePrivacy 2020 Challenge Evaluation Plancited by 6
  9. 2020Pkwrap: a PyTorch Package for LF-MMI Training of Acoustic Modelscited by 5
  10. 2021Exploring the Importance of F0 Trajectories for Speaker Anonymization using X-vectors and Neural Waveform Modelscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 2; 2024: 3; 2025: 2; 2026: 2.

10 papers.

  1. 2022A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairnesscited by 13
  2. 2024End-to-end streaming model for low-latency speech anonymizationcited by 9
  3. 2024A Benchmark for Multi-speaker Anonymizationcited by 7
  4. 2025DarkStream: real-time speech anonymization with low latencycited by 7
  5. 2023DSVAE: Interpretable Disentangled Representation for Synthetic Speech Detectioncited by 6
  6. 2024Exploring VQ-VAE with Prosody Parameters for Speaker Anonymizationcited by 2
  7. 2025Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunitiescited by 2
  8. 2023Vocoder drift compensation by x-vector alignment in speaker anonymisationcited by 1
  9. 2026Anonymization, Not Elimination: Utility-Preserved Speech Anonymizationcited by 1
  10. 2026DiffAnon: Diffusion-based Prosody Control for Voice Anonymizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2022Privacy-Preserving Speech Representation Learning using Vector Quantization
  2. 2026Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstruction
  3. 2021VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversion
  4. 2024QR-VC: Leveraging Quantization Residuals for Linear Disentanglement in Zero-Shot Voice Conversion
  5. 2025SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantization
  6. 2026Voice Anonymization Made Simple: Training-Free Anonymization with Projected Classifier-Free Guidance ↗
  7. 2024Exploratory Evaluation of Speech Content Masking
  8. 2021Improving Security in McAdams Coefficient-Based Speaker Anonymization by Watermarking Method