实现语音模型持续删除指定说话人特征，且不泄露已删除信息。
Continual Speaker Identity Unlearning with Minimal Interference
- 通过参数掩码与正交投影结合，定位并隔离说话人相关权重。
- 在长序列请求下仍能保持已删除说话人特征不可恢复。
- 无需原始数据即可持续更新，适合真实隐私场景使用。
机器遗忘旨在从预训练模型中移除特定概念或知识。近期工作将这一范式拓展至零样本文语转换（ZS-TTS）中的说话人身份遗忘任务，即有选择地消除模型复现某说话人声音的能力。然而，现有方法隐含假设所有遗忘请求同时到达，这不切实际——因隐私驱动的删除请求通常是随时间逐步提出的。我们发现该假设会破坏现有最优方法：每次新说话人遗忘都会完全恢复此前已遗忘的说话人，重新引入本应消除的隐私风险。为此，我们提出累积正交身份抑制框架（CORTIS），这是首个无需访问先前遗忘说话人数据即可实现持续说话人身份遗忘的方案。CORTIS结合基于费舍尔信息的参数掩码（局部化更新至说话人相关权重）与对先前遗忘更新子空间的正交投影。在VoiceBox上，CORTIS可逐个遗忘目标说话人，同时确保此前遗忘的说话人始终无法被复现，显著优于对已有方法的顺序应用。演示地址见 https://cumulativeortis.github.io/。
原文摘要 · Abstract (English)
Machine unlearning removes designated concepts or knowledge from pre-trained models. Recent work has extended this paradigm to speaker identity unlearning in zero-shot text-to-speech (ZS-TTS), the task of selectively erasing a model's ability to replicate a speaker's voice. Existing methods, however, quietly assume all unlearning requests arrive at once; an unrealistic assumption, since privacy-motivated removals arrive sequentially over time. We show this assumption breaks state-of-the-art methods: unlearning each new speaker fully revives previously unlearned speakers, reintroducing the very privacy risk unlearning was meant to eliminate. We present Cumulative ORThogonal Identity Suppression (CORTIS), the first framework for continual speaker identity unlearning in ZS-TTS that requires no access to previously-unlearned speaker data. CORTIS combines Fisher-information-based parameter masking, which localizes updates to speaker-relevant weights, with orthogonal projection against subspaces spanned by prior unlearning updates. With VoiceBox, CORTIS unlearns each requested speaker while keeping previously unlearned speakers forgotten across long request sequences, substantially outperforming sequential application of prior methods. The demo is available at https://cumulativeortis.github.io/ .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。