7 papers
In Defense of Using Worst-case Privacy Disclosure as Privacy Evaluation Metric of Voice Anonymization
Xin Wang, Xiaoxiao Miao
The voice anonymization community mainly uses Equal Error Rate (EER) to evaluate the performance of voice identity protection. While alternative metrics such as privacy-ZEBRA and a…
Target speaker anonymization in multi-speaker recordings
Natalia Tomashenko, Junichi Yamagishi, Xin Wang +2
Most of the existing speaker anonymization research has focused on single-speaker audio, leading to the development of techniques and evaluation metrics optimized for such conditio…
Speaker Privacy and Security in the Big Data Era: Protection and Defense against Deepfake
Liping Chen, Kong Aik Lee, Zhen-Hua Ling +4
In the era of big data, remarkable advancements have been achieved in personalized speech generation techniques that utilize speaker attributes, including voice and speaking style,…
SecureSpeech: Prompt-based Speaker and Content Protection
Belinda Soh Hui Hui, Xiaoxiao Miao, Xin Wang
Given the increasing privacy concerns from identity theft and the re-identification of speakers through content in the speech field, this paper proposes a prompt-based speech gener…
Mitigating Language Mismatch in SSL-Based Speaker Anonymization
Zhe Zhang, Wen-Chin Huang, Xin Wang +2
Speaker anonymization aims to protect speaker identity while preserving content information and the intelligibility of speech. However, most speaker anonymization systems (SASs) ar…
Adapting General Disentanglement-Based Speaker Anonymization for Enhanced Emotion Preservation
Xiaoxiao Miao, Yuxiang Zhang, Xin Wang +3
A general disentanglement-based speaker anonymization system typically separates speech into content, speaker, and prosody features using individual encoders. This paper explores h…