RobustSVC：基于 HuBERT 的旋律提取器与对抗学习，用于鲁棒歌声转换
RobustSVC: HuBERT-based Melody Extractor and Adversarial Learning for Robust Singing Voice Conversion
AI总结：
针对歌声转换中特征提取易受噪声影响的问题，提出 RobustSVC，用基于 HuBERT 的旋律提取器和三判别器对抗训练提升鲁棒性，并在干净与含噪条件下取得更优自然度和相似度。
摘要：
歌声转换（Singing voice conversion, SVC）因在推理阶段使用非鲁棒方法提取音高和能量而受到噪声敏感性的阻碍。由于干净信号对 SVC 中的源音频至关重要，音乐源分离预处理为处理含噪音频（例如带有背景音乐（BGM）的歌声）提供了一种可行方案。然而，现有分离方法难以完全去除噪声，或会过度抑制信号成分，从而影响处理后音频的自然度和相似度。为解决这一问题，本研究提出 RobustSVC，这是一种新颖的任意对一 SVC 框架，可将含噪人声转换为由目标歌手演唱的干净人声。我们用基于 HuBERT 的旋律提取器替换非鲁棒特征，并采用包含三个判别器的对抗训练机制，以减少自监督表征中的信息泄漏。实验结果表明，RobustSVC 具有噪声鲁棒性，并且在含噪和干净人声条件下均比基线方法取得了更高的相似度和自然度。
英文摘要：
Singing voice conversion (SVC) is hindered by noise sensitivity due to the use of non-robust methods for extracting pitch and energy during the inference. As clean signals are key for the source audio in SVC, music source separation preprocessing offers a viable solution for handling noisy audio, like singing with background music (BGM). However, current separating methods struggle to fully remove noise or excessively suppress signal components, affecting the naturalness and similarity of the processed audio. To tackle this, our study introduces RobustSVC, a novel any-to-one SVC framework that converts noisy vocals into clean vocals sung by the target singer. We replace the non-robust feature with a HuBERT-based melody extractor and use adversarial training mechanisms with three discriminators to reduce information leakage in self-supervised representations. Experimental results show that RobustSVC is noise-robust and achieves higher similarity and naturalness than baseline methods in both noisy and clean vocal conditions.
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。
