Skip to Main content Skip to Navigation
Conference papers

Spoofing Speaker Verification With Voice Style Transfer And Reconstruction Loss

Abstract : In this paper we investigate a template reconstruction attack against a speaker verification system. A stolen speaker embedding is processed with a zero-shot voice-style transfer system to reconstruct a Mel-spectrogram containing as much speaker information as possible. We assume the attacker has a black box access to a state-of-the-art automatic speaker verification system. We modify the AutoVC voice-style transfer system to spoof the automatic speaker verification system. We find that integrating a new loss targeting embedding reconstruction and optimizing training hyper-parameters significantly improves spoofing. Results obtained for speaker verification are similar to other biometrics, such as handwritten digits or face verification. We show on standard corpora (VoxCeleb and VCTK) that the reconstructed Mel-spectrograms contain enough speaker characteristics to spoof the original authentication system.
Document type :
Conference papers
Complete list of metadata
Contributor : Thomas Thebaud Connect in order to contact the contributor
Submitted on : Monday, September 27, 2021 - 4:22:52 PM
Last modification on : Tuesday, May 17, 2022 - 11:18:03 AM
Long-term archiving on: : Tuesday, December 28, 2021 - 7:04:43 PM


Files produced by the author(s)


  • HAL Id : hal-03356005, version 1



Thomas Thebaud, Gaël Le Lan, Anthony Larcher. Spoofing Speaker Verification With Voice Style Transfer And Reconstruction Loss. Workshop on Information Forensics and Security, Dec 2021, Montpellier, France. ⟨hal-03356005⟩



Record views


Files downloads