Formed in 2020, the VoicePrivacy initiative has spearheaded efforts to develop privacy-preserving solutions for speech technologies. To date, it has primarily focused on voice anonymization, i.e., transforming speech signals to conceal speaker identity while preserving speech utility. This objective has been pursued through a series of competitive benchmarking challenges, providing common datasets, standardized evaluation protocols, and meaningful metrics for fair comparison of anonymization systems. The first three editions of the VoicePrivacy Challenge (VPC) were held in 2020, 2022, and 2024. The scope of the VoicePrivacy Challenge has progressively evolved. While VPC 2020 established a foundational evaluation framework for English voice anonymization, VPC 2022 extended this framework to assess prosody preservation, and VPC 2024 further introduced explicit requirements on preserving the speaker’s emotional state. Following VPC 2024, the Attacker Challenge was introduced to foster the development of stronger attacker models, evaluated against a selection of top-performing anonymization systems submitted to VPC 2024, as well as strong baseline systems.
VoicePrivacy 2026, the fourth edition of the challenge, starts in March 2026 and culminates in the VoicePrivacy Challenge workshop held in conjunction with the 6th Symposium on Security and Privacy in Speech Communication (SPSC), co-located with Interspeech 2026 in Sydney, Australia.
In keeping with prior editions, the challenge focuses on the subtask of voice anonymization, i.e., altering the speaker’s voice to conceal identity as effectively as possible while preserving linguistic content and relevant paralinguistic attributes. In VPC 2026, particular emphasis is placed on two key aspects. First, the challenge introduces stronger, domain-aware attackers optimized using domain-related data. Specifically, since most state-of-the-art anonymization approaches are based on neural voice conversion (VC) techniques, attacker models are correspondingly trained on diverse VC data to achieve stronger speaker re-identification performance. Second, beyond English anonymization, VPC 2026 explicitly extends the evaluation to a multilingual setting. The challenge is organised with two independent tracks:
Track 1: English anonymization.
Track 2: Multilingual anonymization.
Follow @VoicePrivacy Follow @Voice-Privacy-Challenge
Participants/teams are requested to register for the evaluation. Registration should be performed once only for each participating entity using the registration form.
You will receive a confirmation email within ~24 hours after successful registration. Otherwise, or in case of any questions, please contact the organisers:
organisers@lists.voiceprivacychallenge.org
For updates, all participants and everyone interested in the VoicePrivacy Challenge are encouraged to subscribe to: https://groups.google.com/g/voiceprivacy
The result submission deadline is 30th June 2026. The paper submission deadline is to be confirmed. All participants are invited to present their work at the joint SPSC Symposium and VoicePrivacy Challenge workshop organized in conjunction with Interspeech 2026.
| Deadline | Date |
|---|---|
| Deadline for participants to submit a list for training data and models | 30th April 2026 |
| Publication of the full final list of training data and models | 7th May 2026 |
| Deadline for participants to submit objective evaluation results, anonymized data, and system descriptions | 30th June 2026 |
| Submission of challenge papers to the joint SPSC Symposium and VoicePrivacy Challenge workshop | TBC |
| Author notification for challenge papers | TBC |
| Joint SPSC Symposium and VoicePrivacy Challenge workshop | TBC |
Publicly available resources are used for the training, development, and evaluation of voice anonymization systems.
Full details are in the VoicePrivacy 2026 Evaluation Plan.
The organisers provide baseline anonymization systems and evaluation scripts.
| ID | Description |
|---|---|
| B2 | McAdams coefficients-based (DSP-based anonymization) |
| B3 | Phone aligner + Praat → E2E ASR → GST → FastSpeech2 + HiFi-GAN, GAN speaker selection |
| B4 | HuBERT Base (quantized semantic encoder) + EnCodec |
| B5 | YAAPT → wav2vec2 + TDNN-F + VQ → ECAPA → HiFi-GAN, Select speaker |
| ID | Description |
|---|---|
| BM1 | HuBERT-based, language-independent (similar to legacy B1) |
| BM2 | Whisper + IMS Toucan + HiFi-GAN, full pipeline with prosody and F0 |
| BM3 | Same as BM2 but without prosody extraction and F0/energy modification |
Repository: Voice-Privacy-Challenge-2026
| Metric | Description |
|---|---|
| Privacy | Equal error rate (EER) — semi-informed attacker ASV |
| Utility | WER (ASR), UAR (SER) |
| Evaluation conditions | Minimum target EERs: 10%, 20%, 30%, 40% |
| Metric | Description |
|---|---|
| Privacy | EER — averaged across French, Spanish, English, German |
| Utility | WER (Whisper-large-v3 ASR), UAR (emotion2vec SER) — averaged across languages |
| Evaluation conditions | Same as Track 1: 10%, 20%, 30%, 40% |
Submissions that satisfy a given privacy requirement are ranked by utility (WER and UAR separately).
Deadline: 30th June 2026
Result files:
exp/results_summary/track1/result_for_rank<suffix> (Track 1) or exp/results_summary/track2/result_for_rank<suffix> (Track 2)result_for_submission<suffix>.zipCSV files: ASR, SER, ASV (lazy-informed), ASV (semi-informed) results
Anonymized speech:
System description: Single, detailed system description (2–6 pages, ISCA SPSC format).
Further details will be published via voiceprivacy@googlegroups.com or the VoicePrivacy Challenge website.
Xiaoxiao Miao — Duke Kunshan University, China
Natalia Tomashenko — Université de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France
Ridwan Arefeen — Singapore Institute of Technology, Singapore
Sarina Meyer — Institute for Natural Language Processing, University of Stuttgart, Germany
Michele Panariello — Audio Security and Privacy Group, EURECOM, France
Xin Wang — National Institute of Informatics, Tokyo, Japan
Emmanuel Vincent — Université de Lorraine, CNRS, Inria, LORIA, F-54000 Nancy, France
Nicholas Evans — Audio Security and Privacy Group, EURECOM, France
Junichi Yamagishi — National Institute of Informatics, Tokyo, Japan
Massimiliano Todisco — Audio Security and Privacy Group, EURECOM, France
Xin Wang is partially supported by JST, PRESTO Grant Number JPMJPR23P9, Japan. Part of the baseline experiment was conducted using the TSUBAME4.0 supercomputer of Institute of Science Tokyo.
This work was conducted in the context of the Inria–NII TrustedSpeech Associate Team and was partially supported by the French National Research Agency (ANR) under the Speech Privacy project and the IPoP project of the Cybersecurity PEPR. The experiments were partially carried out using the Grid'5000 testbed.