从A到B再回到A：基于非平行数据的回文零样本语音转换
From A to B to A: Palindromic Zero-Shot Voice Conversion with Non-Parallel Data
AI总结：
提出利用WavLM表示的K近邻检索对齐非平行语音，构建合成训练对，结合说话人损失实现零样本语音转换，在仅用英语数据训练下跨语言表现优异。
摘要：
我们提出一个语音转换（VC）框架，利用WavLM表示上的K近邻（KNN）检索来对齐非平行的源语音和目标语音，从而为监督学习构建合成训练对。检索到的片段作为合成输入，而真实目标音频提供真实输出，形成一种合成到真实的训练范式，该范式自然支持多语言数据，无需平行语料库或显式对齐。为了确保一致的目标说话人身份，我们引入了一个来自预训练说话人验证模型的说话人损失。跨多种语言的实验表明，尽管仅使用英语数据训练，所提出的方法实现了高自然度和强说话人相似性，优于有竞争力的VC基线。样本可在https://palindromic-vc.github.io获取。
英文摘要：
We present a voice conversion (VC) framework that utilizes K-Nearest Neighbors (KNN) retrieval over WavLM representations to align non-parallel source and target speech, constructing synthetic training pairs for supervised learning. The retrieved segments serve as synthetic inputs, while real target audio provides ground-truth outputs, forming a synthetic-to-real training paradigm that naturally supports multilingual data without requiring parallel corpora or explicit alignment. To ensure consistent target-speaker identity, we incorporate a speaker loss derived from a pretrained speaker verification model. Experiments across multiple languages demonstrate that the proposed approach achieves high naturalness and strong speaker similarity, outperforming competitive VC baselines, despite being trained exclusively on English data. Samples can be accessed at: https://palindromic-vc.github.io.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
