S${}^2$Voice: Style-Aware Autoregressive Modeling with Enhanced Conditioning for Singing Style Conversion

Ziqian Wang, Xianjun Xia, Chuanzeng Huang +1

We present S${}^2$Voice, the winning system of the Singing Voice Conversion Challenge (SVCC) 2025 for both the in-domain and zero-shot singing style conversion tracks. Built on the s…