EZ-VC：简易零样本任意到任意语音转换
EZ-VC: Easy Zero-shot Any-to-Any Voice Conversion
AI总结：
本文提出EZ-VC，一种结合自监督离散语音表示与非自回归扩散变换器条件流匹配解码器的零样本任意到任意语音转换方法，无需多编码器，在跨语言场景中表现出色。
摘要：
近年来，语音转换研究日益聚焦于提升现有方法的零样本能力。尽管取得了显著进展，当前架构在零样本跨语言场景下仍往往表现不佳，且常难以泛化到未见语言和口音的说话人。本文采用了一种简单而有效的方法，将自监督模型中的离散语音表示与非自回归的基于扩散变换器的条件流匹配语音解码器相结合。我们证明，该架构使我们能够以纯无文本、自监督的方式训练语音转换模型。我们的技术无需多个编码器来解耦语音特征。我们的模型在零样本跨语言场景中，即使对于未见语言也能表现出色。演示：https://ez-vc.github.io/EZ-VC-Demo/
英文摘要：
Voice Conversion research in recent times has increasingly focused on improving the zero-shot capabilities of existing methods. Despite remarkable advancements, current architectures still tend to struggle in zero-shot cross-lingual settings. They are also often unable to generalize for speakers of unseen languages and accents. In this paper, we adopt a simple yet effective approach that combines discrete speech representations from self-supervised models with a non-autoregressive Diffusion-Transformer based conditional flow matching speech decoder. We show that this architecture allows us to train a voice-conversion model in a purely textless, self-supervised fashion. Our technique works without requiring multiple encoders to disentangle speech features. Our model also manages to excel in zero-shot cross-lingual settings even for unseen languages. For Demo: https://ez-vc.github.io/EZ-VC-Demo/
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。
