Diffusion-based singing voice conversion (SVC) models have shown better
synthesis quality compared to traditional methods. However, in cross-domain SVC
scenarios, where there is a significant disparity in pitch between the source
and target voice domains, the models tend to generate audios with hoarseness,
posing challenges in achieving high-quality vocal outputs. Therefore, in this
paper, we propose a Self-supervised Pitch Augmentation method for Singing Voice
Conversion (SPA-SVC), which can enhance the voice quality in SVC tasks without
requiring additional data or increasing model parameters. We innovatively
introduce a cycle pitch shifting training strategy and Structural Similarity
Index (SSIM) loss into our SVC model, effectively enhancing its performance.
Experimental results on the public singing datasets M4Singer indicate that our
proposed method significantly improves model performance in both general SVC
scenarios and particularly in cross-domain SVC scenarios.

在这篇论文中，我们提出了一种自监督的 SPA-SVC 方法，该方法可以改善 SVC 任务中的声音质量，无需额外的数据或增加模型参数。我们通过引入循环音高转换训练策略和结构相似性指数（SSIM）损失，有效提升了 SVC 模型的性能，实验结果表明我们的方法在一般的 SVC 场景和跨域 SVC 场景中都显著提高了模型性能。