Distinctive and natural speaker anonymization via singular value transformation-assisted matrix

J Yao, Q Wang, P Guo, Z Ning… - IEEE/ACM Transactions …, 2024 - ieeexplore.ieee.org
Speaker anonymization is an effective privacy protection solution that aims to conceal
speaker's identity while preserving the naturalness and distinctiveness of the original …

MUSA: Multi-lingual speaker anonymization via serial disentanglement

J Yao, Q Wang, P Guo, Z Ning, Y Yang, Y Pan… - arxiv preprint arxiv …, 2024 - arxiv.org
Speaker anonymization is an effective privacy protection solution designed to conceal the
speaker's identity while preserving the linguistic content and para-linguistic information of …

NWPU-ASLP system for the voiceprivacy 2022 challenge

J Yao, Q Wang, L Zhang, P Guo, Y Liang… - arxiv preprint arxiv …, 2022 - arxiv.org
This paper presents the NWPU-ASLP speaker anonymization system for VoicePrivacy 2022
Challenge. Our submission does not involve additional Automatic Speaker Verification …

Salt: Distinguishable speaker anonymization through latent space transformation

Y Lv, J Yao, P Chen, H Zhou, H Lu… - 2023 IEEE Automatic …, 2023 - ieeexplore.ieee.org
Speaker anonymization aims to conceal a speaker's identity without degrading speech
quality and intelligibility. Most speaker anonymization systems disentangle the speaker …

Anonymizing speaker voices: Easy to imitate, difficult to recognize?

J Williams, K Pizzi, N Tomashenko… - ICASSP 2024-2024 …, 2024 - ieeexplore.ieee.org
A vastly under-explored area in speech anonymization involves characterizing how different
speakers perform in voice privacy tasks. In this paper, we present a deeper analysis by …

Linear frequency residual cepstral features for replay spoof detection on asvspoof 2019

P Gupta, HA Patil - 2022 30th European Signal Processing …, 2022 - ieeexplore.ieee.org
Playing a pre-recorded speech to gain illegal access to Automatic Speaker Verification
(ASV) system is one of the easiest attacks to execute but difficult to detect. Such attacks are …