# Voice Privacy from an Attribute-based Perspective

arXiv: https://arxiv.org/abs/2603.20301 · HTML: https://mlsanity.com/paper/2603.20301/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [ECAPA-TDNN: Emphasized Channel Attention, Propagation and Aggregation in TDNN Based Speaker Verification](https://mlsanity.com/paper/2005.07143/) (2020)
- [The VoicePrivacy 2020 Challenge: Results and findings](https://mlsanity.com/paper/2109.00648/) (2021)
- [The VoicePrivacy 2024 Challenge Evaluation Plan](https://mlsanity.com/paper/2404.02677/) (2024)
- [Speaker anonymisation using the McAdams coefficient](https://mlsanity.com/paper/2011.01130/) (2020)
- [Anonymizing Speech: Evaluating and Designing Speaker Anonymization Techniques](https://mlsanity.com/paper/2308.04455/) (2023)
- [Speaker anonymization using neural audio codec language models](https://mlsanity.com/paper/2309.14129/) (2023)
- [VoxCeleb Enrichment for Age and Gender Recognition](https://mlsanity.com/paper/2109.13510/) (2021)
- [MUSA: Multi-lingual Speaker Anonymization via Serial Disentanglement](https://mlsanity.com/paper/2407.11629/) (2024)
- [A Benchmark for Multi-speaker Anonymization](https://mlsanity.com/paper/2407.05608/) (2024)
- [Leveraging speaker attribute information using multi task learning for speaker verification and diarization](https://mlsanity.com/paper/2010.14269/) (2020)
- [Privacy in Speech Technology](https://mlsanity.com/paper/2305.05227/) (2023)

## Abstract (arXiv)

Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure speaker protection based on signal-to-signal comparisons. In this paper, we introduce an attribute-based perspective, where we measure privacy protection in terms of comparisons between sets of speaker attributes. First, we analyze privacy impact by calculating speaker uniqueness for ground truth attributes, attributes inferred on the original speech, and attributes inferred on speech protected with standard anonymization. Next, we examine a threat scenario involving only a single utterance per speaker and calculate attack error rates. Overall, we observe that inferred attributes still present a risk despite attribute inference errors. Our research points to the importance of considering both attribute-related threats and protection mechanisms in future voice privacy research.