@article{investigatingonincorporatingpretrainedan,
  title = {Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech},
  author = {Chung-Ming Chien and Jheng-Hao Lin and Chien-yu Huang and Po-chun Hsu and Hung-Yi Lee},
  year = {2021},
  eprint = {2103.04088},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2103.04088v5},
}