@inproceedings{chen2024stylefusion,
  title = {StyleFusion TTS: Multimodal Style-Control and Enhanced Feature Fusion for Zero-Shot Text-to-Speech Synthesis},
  author = {Zhiyong Chen and Xinnuo Li and Zhiqi Ai and Shugong Xu},
  year = {2024},
  booktitle = {Pattern Recognition and Computer Vision (PRCV 2024)},
  pages = {263--277},
  doi = {10.1007/978-981-97-8795-1_18}
}