HALL-E: Hierarchical Neural Codec Language Model for Minute-Long Zero-Shot Text-to-Speech Synthesis

Open Webpage

Yuto Nishimura, Takumi Hirose, Masanari Ohi, Hideki Nakayama, Nakamasa Inoue

Published: 01 Jan 2025, Last Modified: 19 May 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0