大数据2026，Vol.12Issue(4)：137-146,10.DOI:10.11959/j.issn.2096-6652.2026059
基于隐空间拼接与对比学习的语音匿名方法研究
Research on speaker anonymization method via latent space splicing and contrastive learning
摘要
Abstract
With the widespread application of speech technology,voice privacy protection faces severe challenges.A speech anonymization method(kLCAnoy++)based on latent space splicing and contrastive learning was proposed,aiming to effectively remove speaker identity information while preserving speech content intelligibility and naturalness.The method first employed the pretrained WavLM model to extract self-supervised speech features.Subsequently,it matched target features in a diverse reference audio feature library using the k-nearest neighbors algorithm,achieving latent space feature splicing to generate preliminary anonymized speech.Finally,a contrastive learning mechanism was introduced,treating natural splicing as positive samples and k-nearest neighbor splicing as negative samples,to optimize the vocoder decoding process and enhance the coherence and naturalness of anonymized speech.Experiments on the VCTK dataset demonstrated that the proposed method significantly outperformed baseline approaches,with visualization analysis further confirming its effectiveness in disentangling speaker identity information.关键词
语音匿名化/说话人去标识/自监督语音表示/隐空间特征拼接/对比学习Key words
speech anonymization/speaker de-identification/self-supervised speech representations/latent space splicing/contrastive learning分类
信息技术与安全科学引用本文复制引用
张旭龙,瞿晓阳,倪晓俊,田晖,王健宗..基于隐空间拼接与对比学习的语音匿名方法研究[J].大数据,2026,12(4):137-146,10.基金项目
深港联合基金(A类)项目(No.SGDX20240115103359001) The Shenzhen-Hong Kong Joint Funding Project(Category A)(No.SGDX20240115103359001) （A类）
