A key challenge of speaker de-identification is the balance between privacy and utility. Many utility variables, such as the cognitive health status of the speaker, are correlated with the privacy variable, such as the speaker identity, violating the independence assumption held by the disentanglement-based approaches, causing leakage of private information and the loss of useful information for downstream tasks. To tackle this challenge, we propose a general framework, DDPO-VC, for speaker de-identification through reinforcement learning-based post-training with diffusion models. Learning from reward signals combining knowledge from privacy-focused and utility-focused teachers, our method outperforms various strong \deid/ methods in both privacy preservation and cognitive utility on two commonly used dementia speech benchmarks. Please check out our code\footnote{\href{https://github.com/cactuswiththoughts/DDPO-VC}{https://github.com/cactuswiththoughts/DDPO-VC}} and demo\footnote{\href{https://cactuswiththoughts.github.io/SpeakerDeID-Demo/}{https://cactuswiththoughts.github.io/SpeakerDeID-Demo/}}.

翻译：说话人去身份化面临隐私保护与效用性权衡的关键挑战。许多效用性变量（如说话人的认知健康状况）与隐私变量（如说话人身份）存在相关性，这违反了基于解耦方法所假设的独立性条件，导致隐私泄露及下游任务有用信息的损失。为解决该问题，我们提出通用框架DDPO-VC，通过基于强化学习的扩散模型后训练实现说话人去身份化。该方法通过融合隐私导向与效用导向教师的奖励信号进行学习，在两个常用痴呆症语音基准测试中，其在隐私保护与认知效用性方面均优于多种强去身份化方法。代码\footnote{\href{https://github.com/cactuswiththoughts/DDPO-VC}{https://github.com/cactuswiththoughts/DDPO-VC}}和演示\footnote{\href{https://cactuswiththoughts.github.io/SpeakerDeID-Demo/}{https://cactuswiththoughts.github.io/SpeakerDeID-Demo/}}已开放获取。