@article{emiliaalargescaleextensivemultilingual, title = {Emilia: A Large-Scale, Extensive, Multilingual, and Diverse Dataset for Speech Generation}, author = {Haorui He and Zengqiang Shang and Chaoren Wang and Xuyuan Li and Yicheng Gu and Hua Hua and Liwei Liu and Chen Yang and Jiaqi Li and Peiyang Shi and Yuancheng Wang and Kai Chen and Pengyuan Zhang and Zhizheng Wu}, year = {2025}, eprint = {2501.15907}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2501.15907v1}, }