mlsanityData to 13 Oct 2026

Probing the Feasibility of Multilingual Speaker Anonymization

arXiv 2407.02937 ↗First posted 3 Jul 2024cs.CL cs.SD eess.AScited by 5

Not on the map. Why?

Abstract (arXiv)

In speaker anonymization, speech recordings are modified in a way that the identity of the speaker remains hidden. While this technology could help to protect the privacy of individuals around the globe, current research restricts this by focusing almost exclusively on English data. In this study, we extend a state-of-the-art anonymization system to nine languages by transforming language-dependent components to their multilingual counterparts. Experiments testing the robustness of the anonymized speech against privacy attacks and speech deterioration show an overall success of this system for all languages. The results suggest that speaker embeddings trained on English data can be applied across languages, and that the anonymization performance for a language is mainly affected by the quality of the speech synthesis component used for it.

Key facts. Cited by 5 papers in the map (data through 13 Oct 2026). Builds on 28 of its 35 references that are in the map. First posted on arXiv 3 Jul 2024.

Builds on

28 of 35 references.

References · 28

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 4,004
  2. 2019Common Voice: A Massively-Multilingual Speech Corpuscited by 1,366
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,148
  4. 2018VoxCeleb2: Deep Speaker Recognitioncited by 864
  5. 2017VoxCeleb: a large-scale speaker identification datasetcited by 719
  6. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 715
  7. 2020ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verificationcited by 612
  8. 2020MLS: A Large-Scale Multilingual Dataset for Speech Researchcited by 468
  9. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  10. 2023Scaling Speech Technology to 1,000+ Languagescited by 402
  11. 2018Style Tokens: Unsupervised Style Modeling, Control and Transfer in End-to-End Speech Synthesiscited by 259
  12. 2021The VoicePrivacy 2020 Challenge: Results and findingscited by 45
16 more
  1. 2019Speaker Anonymization Using X-vector and Neural Waveform Modelscited by 41
  2. 2022AdaSpeech 4: Adaptive Text to Speech in Zero-Shot Scenarioscited by 41
  3. 2020Speaker anonymisation using the McAdams coefficientcited by 38
  4. 2022Anonymizing Speech with Generative Adversarial Networks to Preserve Speaker Privacycited by 20
  5. 2022The VoicePrivacy 2022 Challenge Evaluation Plancited by 18
  6. 2023Speaker anonymization using orthogonal Householder neural networkcited by 18
  7. 2022Differentially Private Speaker Anonymizationcited by 16
  8. 2022Low-Resource Multilingual and Zero-Shot Multispeaker TTScited by 15
  9. 2022Language-Independent Speaker Anonymization Approach using Self-Supervised Pre-Trained Modelscited by 14
  10. 2022Exact Prosody Cloning in Zero-Shot Multispeaker Text-to-Speechcited by 13
  11. 2022Improving speaker de-identification with functional data analysis of f0 trajectoriescited by 12
  12. 2022Speaker Anonymization with Phonetic Intermediate Representationscited by 9
  13. 2022Analyzing Language-Independent Speaker Anonymization Framework under Unseen Conditionscited by 6
  14. 2023The IMS Toucan System for the Blizzard Challenge 2023cited by 6
  15. 2023VoicePAT: An Efficient Open-source Evaluation Toolkit for Voice Privacy Researchcited by 3
  16. 2023Vocoder drift in x-vector-based speaker anonymizationcited by 2

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2025: 3; 2026: 2.

5 papers.

  1. 2026The Third VoicePrivacy Challenge: Preserving Emotional Expressiveness and Linguistic Content in Voice Anonymizationcited by 8
  2. 2025Multilingual Source Tracing of Speech Deepfakes: A First Benchmarkcited by 7
  3. 2025A Survey of Code-switched Arabic NLP: Progress, Challenges, and Future Directionscited by 5
  4. 2025SEF-MK: Speaker-Embedding-Free Voice Anonymization through Multi-k-means Quantizationcited by 1
  5. 2026Your Voice Cloning System is Secretly a Voice Anonymizercited by 0