Exploring the importance of f0 trajectories for speaker anonymization using x-vectors and neural waveform models

ÜE Gaznepoglu, N Peters - arXiv preprint arXiv:2110.06887, 2021 - arxiv.org
Voice conversion for speaker anonymization is an emerging field in speech processing
research. Many state-of-the-art approaches are based on the resynthesis of the phoneme …

Deep learning-based f0 synthesis for speaker anonymization

ÜE Gaznepoglu, N Peters - 2023 31st European Signal …, 2023 - ieeexplore.ieee.org
Voice conversion for speaker anonymization is an emerging concept for privacy protection.
In a deep learning setting, this is achieved by extracting multiple features from speech …

Evaluation of the Speech Resynthesis Capabilities of the VoicePrivacy Challenge Baseline B1

ÜE Gaznepoglu, N Peters - arXiv preprint arXiv:2308.11337, 2023 - arxiv.org
Speaker anonymization systems continue to improve their ability to obfuscate the original
speaker characteristics in a speech signal, but often create processing artifacts and …