mlsanityData to 7 Oct 2026

Introducing the VoicePrivacy Initiative

arXiv 2005.01387 ↗First posted 4 May 2020cs.CLcited by 48

Not on the map. Why?

Abstract (arXiv)

The VoicePrivacy initiative aims to promote the development of privacy preservation tools for speech technology by gathering a new community to define the tasks of interest and the evaluation methodology, and benchmarking solutions through a series of challenges. In this paper, we formulate the voice anonymization task selected for the VoicePrivacy 2020 Challenge and describe the datasets used for system development and evaluation. We also present the attack models and the associated objective and subjective evaluation metrics. We introduce two anonymization baselines and report objective evaluation results.

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 May 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 12; 2023: 5; 2024: 10; 2025: 8; 2026: 5.

48 papers.

Sort:

  1. 2021The VoicePrivacy 2020 Challenge: Results and findingscited by 45
  2. 2024The VoicePrivacy 2024 Challenge Evaluation Plancited by 39
  3. 2022Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacycited by 20
  4. 2022The VoicePrivacy 2022 Challenge Evaluation Plancited by 18
  5. 2022Differentially Private Speaker Anonymizationcited by 16
  6. 2022Improving speaker de-identification with functional data analysis of f0 trajectoriescited by 11
  7. 2022Resource-Efficient Separation Transformercited by 11
  8. 2024The Impact of Speech Anonymization on Pathology and Its Limitscited by 11
  9. 2021Privacy attacks for automatic speech recognition acoustic models in a federated learning frameworkcited by 10
  10. 2022Are disentangled representations all you need to build speaker anonymization systems?cited by 10
  11. 2022Speaker Anonymization with Phonetic Intermediate Representationscited by 9
  12. 2024Privacy versus Emotion Preservation Trade-offs in Emotion-Preserving Speaker Anonymizationcited by 9
36 more
  1. 2021Learning De-identified Representations of Prosody from Raw Audiocited by 8
  2. 2026The Third VoicePrivacy Challenge: Preserving Emotional Expressiveness and Linguistic Content in Voice Anonymizationcited by 8
  3. 2021Configurable Privacy-Preserving Automatic Speech Recognitioncited by 7
  4. 2023Federated Learning for ASR based on Wav2vec 2.0cited by 7
  5. 2023SAIC: Integration of Speech Anonymization and Identity Classificationcited by 7
  6. 2022The VoicePrivacy 2020 Challenge Evaluation Plancited by 6
  7. 2025DarkStream: real-time speech anonymization with low latencycited by 6
  8. 2021Protecting gender and identity with disentangled speech representationscited by 5
  9. 2022Generating gender-ambiguous voices for privacy-preserving speech recognitioncited by 5
  10. 2024Analysis of Speech Temporal Dynamics in the Context of Speaker Verification and Voice Anonymizationcited by 5
  11. 2021On the invertibility of a voice privacy system using embedding alignementcited by 4
  12. 2022Fantomas: Understanding Face Anonymization Reversibilitycited by 4
  13. 2024Differential privacy enables fair and accurate AI-based analysis of speech disorders while protecting patient datacited by 4
  14. 2025The First VoicePrivacy Attacker Challengecited by 4
  15. 2026TVTSyn: Content-Synchronous Time-Varying Timbre for Streaming Voice Conversion and Anonymizationcited by 4
  16. 2022Sotto Voce: Federated Speech Recognition with Differential Privacy Guaranteescited by 3
  17. 2024Prosody-Driven Privacy-Preserving Dementia Detectioncited by 3
  18. 2025Exploiting Context-dependent Duration Features for Voice Anonymization Attack Systemscited by 3
  19. 2024Asynchronous Voice Anonymization Using Adversarial Perturbation On Speaker Embeddingcited by 2
  20. 2021Evaluating X-vector-based Speaker Anonymization under White-box Assessmentcited by 1
  21. 2022DeID-VC: Speaker De-identification via Zero-shot Pseudo Voice Conversioncited by 1
  22. 2023Evaluation of Speaker Anonymization on Emotional Speechcited by 1
  23. 2023Vocoder drift compensation by x-vector alignment in speaker anonymisationcited by 1
  24. 2024SEBA: Strong Evaluation of Biometric Anonymizationscited by 1
  25. 2025You Are What You Say: Exploiting Linguistic Content for VoicePrivacy Attackscited by 1
  26. 2025SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantizationcited by 1
  27. 2025Target speaker anonymization in multi-speaker recordingscited by 1
  28. 2021Preliminary study on using vector quantization latent spaces for TTS/VC systems with consistent performancecited by 0
  29. 2023Beyond Neural-on-Neural Approaches to Speaker Gender Protectioncited by 0
  30. 2024Scenario of Use Scheme: Threat Model Specification for Speaker Privacy Protection in the Medical Domaincited by 0
  31. 2024The First VoicePrivacy Attacker Challenge Evaluation Plancited by 0
  32. 2025Perceptual implications of automatic anonymization in pathological speechcited by 0
  33. 2025Improving the Speaker Anonymization Evaluation's Robustness to Target Speakers with Adversarial Learningcited by 0
  34. 2026DAST: A Dual-Stream Voice Anonymization Attacker with Staged Trainingcited by 0
  35. 2026Child-Centric Voice Anonymization in Single and Multi-Speaker Speech via Domain-Adapted SSL Modelscited by 0
  36. 2026Your Voice Cloning System is Secretly a Voice Anonymizercited by 0