@article{hallehierarchicalneuralcodeclanguage, title = {HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis}, author = {Yuto Nishimura and Takumi Hirose and Masanari Ohi and Hideki Nakayama and Nakamasa Inoue}, year = {2024}, eprint = {2410.04380}, archivePrefix = {arXiv}, url = {https://arxiv.org/abs/2410.04380v1}, }