ClearMask: Noise-Free and Naturalness-Preserving Protection Against Voice Deepfake Attacks
Open Access
- 24 August 2025
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 696-709
Abstract
No abstract availableAll Related Versions
Funding Information
- NSF (National Science Foundation) (2310207)
This publication has 23 references indexed in Scilit:
- Robust Speaker Verification Using Population-Based Data Augmentation2022
- Differentiable Signal Processing With Black-Box Audio Effects2021
- Again-VC: A One-Shot Voice Conversion Using Activation Guidance and Adaptive Instance Normalization2021
- Defending Your Voice: Adversarial Attack on Voice Conversion2021
- Audio Style Transfer2018
- Generalized End-to-End Loss for Speaker Verification2018
- A study on data augmentation of reverberant speech for robust speech recognition2017
- Image Style Transfer Using Convolutional Neural Networks2016
- Statistics of natural reverberation enable perceptual separation of sound and spaceProceedings of the National Academy of Sciences, 2016
- Librispeech: An ASR corpus based on public domain audio books2015