@inproceedings{53bbb34019134569addccc77a8ebdb34,
title = "Salt: Distinguishable Speaker Anonymization Through Latent Space Transformation",
abstract = "Speaker anonymization aims to conceal a speaker's identity without degrading speech quality and intelligibility. Most speaker anonymization systems disentangle the speaker representation from the original speech and achieve anonymization by averaging or modifying the speaker representation. However, the anonymized speech is subject to reduction in pseudo speaker distinctiveness, speech quality and intelligibility for out-of-distribution speaker. To solve this issue, we propose SALT, a Speaker Anonymization system based on Latent space Transformation. Specifically, we extract latent features by a self-supervised feature extractor and randomly sample multiple speakers and their weights, and then interpolate the latent vectors to achieve speaker anonymization. Meanwhile, we explore the extrapolation method to further extend the diversity of pseudo speakers. Experiments on Voice Privacy Challenge dataset show our system achieves a state-of-the-art distinctiveness metric while preserving speech quality and intelligibility. Our code and demo is availible at github11https://github.com/BakerBunker/SALT",
keywords = "speaker anonymization, speech synthesis, voice conversion, voice privacy",
author = "Yuanjun Lv and Jixun Yao and Peikun Chen and Hongbin Zhou and Heng Lu and Lei Xie",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023 ; Conference date: 16-12-2023 Through 20-12-2023",
year = "2023",
doi = "10.1109/ASRU57964.2023.10389719",
language = "英语",
series = "2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2023 IEEE Automatic Speech Recognition and Understanding Workshop, ASRU 2023",
}