Author name: Sihan Lv, Yechen Jin, Zhen Li, Jintao Chen, Jinshan Zhang, Ying Li, Jianwei Yin, Meng Xi

arXiv:2604.16056v1 Announce Type: cross
Abstract: Text-based speech editing aims to modify specific segments while preserving speaker identity and acoustic context. Existing methods rely on task-specific training, which incurs high data costs and stru…