mlsanityData to 14 Oct 2026

The Third VoicePrivacy Challenge: Preserving Emotional Expressiveness and Linguistic Content in Voice Anonymization

arXiv 2601.11846 ↗First posted 17 Jan 2026cs.CL cs.SD eess.AScited by 8

Not on the map. Why?

Abstract (arXiv)

We present results and analyses from the third VoicePrivacy Challenge held in 2024, which focuses on advancing voice anonymization technologies. The task was to develop a voice anonymization system for speech data that conceals a speaker's voice identity while preserving linguistic content and emotional state. We provide a systematic overview of the challenge framework, including detailed descriptions of the anonymization task and datasets used for both system development and evaluation. We outline the attack model and objective evaluation metrics for assessing privacy protection (concealing speaker voice identity) and utility (content and emotional state preservation). We describe six baseline anonymization systems and summarize the innovative approaches developed by challenge participants. Finally, we provide key insights and observations to guide the design of future VoicePrivacy challenges and identify promising directions for voice anonymization research.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 78 of its 124 references that are in the map. First posted on arXiv 17 Jan 2026.

Builds on

78 of 124 references.

References · 78

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,057
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,905
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,342
  4. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,657
  5. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,384
  6. 2014On the Properties of Neural Machine Translation: Encoder-Decoder Approachescited by 1,304
  7. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
  8. 2018VoxCeleb2: Deep Speaker Recognitioncited by 875
  9. 2023Neural Codec Language Models are Zero-Shot Text to Speech Synthesizerscited by 752
  10. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 717
  11. 2022High Fidelity Neural Audio Compressioncited by 687
  12. 2019LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speechcited by 649
38 more
  1. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 628
  2. 2021XLS-R: Self-supervised Cross-lingual Speech Representation Learning at Scalecited by 601
  3. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
  4. 2019Libri-Light: A Benchmark for ASR with Limited or No Supervisioncited by 467
  5. 2015MUSAN: A Music, Speech, and Noise Corpuscited by 425
  6. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 406
  7. 2021W2v-BERT: Combining Contrastive Learning and Masked Language Modeling for Self-Supervised Speech Pre-Trainingcited by 347
  8. 2020FSD50K: An Open Dataset of Human-Labeled Sound Eventscited by 342
  9. 2018Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesiscited by 259
  10. 2022Dawn of the transformer era in speech emotion recognition: closing the valence gapcited by 157
  11. 2022Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understandingcited by 91
  12. 2022FreeVC: Towards High-Quality Text-Free One-Shot Voice Conversioncited by 80
  13. 2022ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakerscited by 74
  14. 2023Voice Conversion With Just Nearest Neighborscited by 68
  15. 2021VQMIVC: Vector Quantization and Mutual Information-Based Unsupervised Speech Representation Disentanglement for One-shot Voice Conversioncited by 64
  16. 2022ICASSP 2022 Deep Noise Suppression Challengecited by 60
  17. 2020Introducing the VoicePrivacy Initiativecited by 49
  18. 2021The VoicePrivacy 2020 Challenge: Results and findingscited by 46
  19. 2020Fairness in Biometrics: a figure of merit to assess biometric verification systemscited by 41
  20. 2020Speaker anonymisation using the McAdams coefficientcited by 38
  21. 2019Evaluating Voice Conversion-based Privacy Protection against Informed Attackerscited by 31
  22. 2020x-vectors meet emotions: A study on dependencies between emotion and speaker recognitioncited by 31
  23. 2020Design Choices for X-vector Based Speaker Anonymizationcited by 27
  24. 2023Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniquescited by 22
  25. 2024ECAPA2: A Hybrid Neural Network Architecture and Training Strategy for Robust Speaker Embeddingscited by 22
  26. 2022Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacycited by 21
  27. 2022Evaluating Proposed Fairness Models for Face Recognition Algorithmscited by 18
  28. 2022The VoicePrivacy 2022 Challenge Evaluation Plancited by 18
  29. 2023Speaker anonymization using orthogonal Householder neural networkcited by 18
  30. 2024The VoicePrivacy 2022 Challenge: Progress and Perspectives in Voice Anonymisationcited by 17
  31. 2022A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systemscited by 15
  32. 2022Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Unitscited by 15
  33. 2022Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Modelscited by 14
  34. 2024NPU-NTU System for Voice Privacy 2024 Challengecited by 14
  35. 2024The Impact of Speech Anonymization on Pathology and Its Limitscited by 11
  36. 2024MUSA: Multi-lingual Speaker Anonymization via Serial Disentanglementcited by 10
  37. 2024Privacy versus Emotion Preservation Trade-offs in Emotion-Preserving Speaker Anonymizationcited by 10
  38. 2024HLTCOE JHU Submission to the Voice Privacy Challenge 2024cited by 10

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026StreamVoiceAnon+: Emotion-Preserving Streaming Speaker Anonymization via Frame-Level Acoustic Distillationcited by 1
  2. 2026DAST: A Dual-Stream Voice Anonymization Attacker with Staged Trainingcited by 1
  3. 2026DiffAnon: Diffusion-based Prosody Control for Voice Anonymizationcited by 0
  4. 2026Child-Centric Voice Anonymization in Single and Multi-Speaker Speech via Domain-Adapted SSL Modelscited by 0
  5. 2026NouveauVoice: Generating Novel Pseudo Speakers for Voice Anonymizationcited by 0
  6. 2026Listen to the Features: Voice Anonymization Driven by Content Embedding Matching over Signal Reconstructioncited by 0
  7. 2026Hearing the Whispers: Black-Box Membership Inference Attacks on Finetuned TTS Modelscited by 0
  8. 2026Forget who you Forgot: Speaker Unlearning to Prevent Re-Identification in Zero-Shot Text-to-Speechcited by 0