@article{learningutterancelevelrepresentations,
  title = {Learning utterance-level representations through token-level acoustic latents prediction for Expressive Speech Synthesis},
  author = {Karolos Nikitaras and Konstantinos Klapsas and Nikolaos Ellinas and Georgia Maniati and June Sig Sung and Inchul Hwang and Spyros Raptis and Aimilios Chalamandaris and Pirros Tsiakoulis},
  year = {2022},
  eprint = {2211.00523},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2211.00523v1},
}