Language-independent speaker anonymization with multiple privacy-related attributes

第一年在说话人匿名化方面的工作包括三个部分：第一部分)根据我们的计划，我们提出了修改说话人嵌入和基音以隐藏说话人性别的方法。这一方法已被ICASSP 2023接受。我们的代码和音频样本是可用的。(参见https://github.com/NII-yamagishilab/speaker_sex_attribute_privacy)Part 2)我为语音隐私2022挑战做出了贡献，并构建了一个基于自我监督学习的说话人匿名系统。它使用基于SSL的内容编码器来提取通用的上下文表示，而不考虑输入语音的语言。这个模型是免费发布的(见SSL3)我们对前面提到的基于https://www.voiceprivacychallenge.org).Part的程序进行了修改，目的是让用户更容易操作。我们添加了几个新功能，包括以灵活的方式调整音调和选择要匿名的扬声器。这个更新的程序随后被应用于日语语音数据。日本的一家广播公司表示有兴趣将这种模式用于真实的电视节目。

The first year's work on speaker anonymization includes three parts:Part 1) Following our plan, we propose modifying the speaker embedding and pitch to conceal the speaker's gender. This approach has been accepted by ICASSP 2023. Our code and audio samples is available. (see https://github.com/ nii- yamagishilab/speaker_sex_attribute_privacy)Part 2) I contributed to the VoicePrivacy 2022 challenge and built a self-supervised learning (SSL) -based speaker anonymization system (SAS). It uses an SSL-based content encoder to extract general context representations regardless of the language of the input speech. This model is released for free (see https://www.voiceprivacychallenge.org).Part 3) We made changes to the SSL-based SAS program mentioned earlier, with the goal of making it easier for users to operate. We added several new features, including the ability to adjust pitch and select speakers to anonymize in a flexible way. This updated program was then applied to Japanese speech data. A broadcasting company in Japan has expressed interest in using this model for a real TV program.