# Voice Conversion-based Privacy through Adversarial Information Hiding

arXiv: https://arxiv.org/abs/2409.14919 · HTML: https://mlsanity.com/paper/2409.14919/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2024.

## Built on by (most cited first, 2 of 2)

- [Exploiting Context-dependent Duration Features for Voice Anonymization Attack Systems](https://mlsanity.com/paper/2507.15214/) (2025)
- [Target speaker anonymization in multi-speaker recordings](https://mlsanity.com/paper/2510.09307/) (2025)

## Abstract (arXiv)

Privacy-preserving voice conversion aims to remove only the attributes of speech audio that convey identity information, keeping other speech characteristics intact. This paper presents a mechanism for privacy-preserving voice conversion that allows controlling the leakage of identity-bearing information using adversarial information hiding. This enables a deliberate trade-off between maintaining source-speech characteristics and modification of speaker identity. As such, the approach improves on voice-conversion techniques like CycleGAN and StarGAN, which were not designed for privacy, meaning that converted speech may leak personal information in unpredictable ways. Our approach is also more flexible than ASR-TTS voice conversion pipelines, which by design discard all prosodic information linked to textual content. Evaluations show that the proposed system successfully modifies perceived speaker identity whilst well maintaining source lexical content.