Skip to yearly menu bar Skip to main content

Workshop: Machine Learning for Audio

Leveraging Content-based Features from Multiple Acoustic Models for Singing Voice Conversion

Xueyao Zhang · Yicheng Gu · Haopeng Chen · Zihao Fang · Lexiao Zou · Liumeng Xue · Zhizheng Wu


Singing voice conversion (SVC) is a technique to enable an arbitrary singer to sing an arbitrary song. To achieve that, it is important to obtain speaker-agnostic representations from source audio, which is a challenging task. A common solution is to extract content-based features (e.g., PPGs) from a pretrained acoustic model. However, the choices for acoustic models are vast and varied. It is yet to be explored what characteristics of content features from different acoustic models are, and whether integrating multiple content features can help each other. This study investigates three distinct content features, sourcing from WeNet, Whisper, and ContentVec, respectively. We explore their complementary roles in intelligibility, prosody, and conversion similarity for SVC. By integrating the multiple content features with a diffusion-based SVC model, our SVC system achieves superior conversion performance on both objective and subjective evaluation in comparison to a single source of content features.

Chat is not available.