@article{finetuningtexttospeechdiffusionmodelsusi,
  title = {Fine-Tuning Text-to-Speech Diffusion Models Using Reinforcement Learning with Human Feedback},
  author = {Jingyi Chen and Ju Seung Byun and Micha Elsner and Pichao Wang and Andrew Perrault},
  year = {2025},
  eprint = {2508.03123},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2508.03123},
}