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/ .

翻译：摘要：机器遗忘是指从预训练模型中移除特定概念或知识。近期研究将该范式扩展至零样本文本转语音（ZS-TTS）中的说话人身份遗忘，即选择性擦除模型复制特定说话人声音能力的任务。然而，现有方法默认所有遗忘请求同时到达——这一假设并不现实，因为出于隐私动机的删除请求会随时间顺序到达。我们证明这一假设会破坏现有最优方法：每遗忘一个新说话人会使先前已遗忘的说话人完全恢复，从而重新引入遗忘本应消除的隐私风险。我们提出累积正交身份抑制（CORTIS），这是首个面向ZS-TTS中连续说话人身份遗忘的框架，无需访问先前已遗忘的说话人数据。CORTIS结合基于Fisher信息的参数掩码（将更新局限于与说话人相关的权重）与针对先前遗忘更新所张成子空间的正交投影。在使用VoiceBox的实验表明，CORTIS在长序列请求中不仅能遗忘每个请求的说话人，还能保持先前已遗忘的说话人被彻底遗忘，性能显著优于对现有方法的顺序应用。演示视频见https://cumulativeortis.github.io/。