X-Vector Singular Value Modification and Statistical-Based Decomposition with Ensemble Regression Modeling for Speaker Anonymization System
X-Vector Singular Value Modification and Statistical-Based Decomposition with Ensemble Regression Modeling for Speaker Anonymization System
复制标题
DOI：
10.21437/interspeech.2020-1887
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Candy Olivia Mawalim;Kasorn Galajit;Jessada Karnjana;M. Unoki
中科院分区：
文献类型：
--
作者：
Candy Olivia Mawalim;Kasorn Galajit;Jessada Karnjana;M. Unoki
匿名化说话人的个性是确保语音隐私保护的关键。在本文中，我们提出了一个基于集合回归模型的说话人个性匿名化系统，该系统在x向量上使用奇异值修正和基于统计的分解。匿名化系统需要说话人对说话人的对应（每个说话人对应一个伪说话人），这可以通过修改重要的x向量元素来实现。通过奇异值分解和变异分析确定显著元素。随后，使用基于聚类的伪目标的x向量池训练的集成回归模型执行匿名化过程。结果表明，我们提出的匿名化系统通过保持与voicepprivacy 2020挑战赛中引入的基线系统相似的可理解性分数，有效地提高了客观可验证性，特别是在匿名试验和匿名入学设置中。
Anonymizing speaker individuality is crucial for ensuring voice privacy protection. In this paper, we propose a speaker individ-uality anonymization system that uses singular value modifi-cation and statistical-based decomposition on an x-vector with ensemble regression modeling. An anonymization system requires speaker-to-speaker correspondence (each speaker corresponds to a pseudo-speaker), which may be possible by modifying significant x-vector elements. The significant elements were determined by singular value decomposition and variant analysis. Subsequently, the anonymization process was performed by an ensemble regression model trained using x-vector pools with clustering-based pseudo-targets. The results demonstrated that our proposed anonymization system effectively improves objective verifiability, especially in anonymized trials and anonymized enrollments setting, by preserving similar intelligibility scores with the baseline system introduced in the VoicePrivacy 2020 Challenge.