HiddenSinger: High-quality singing voice synthesis via neural audio codec and latent diffusion models

Download PDF
Open Webpage

Ji-Sang Hwang, Sang-Hoon Lee, Seong-Whan Lee

Published: 01 Jan 2025, Last Modified: 14 May 2025Neural Networks 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•Introduce HiddenSinger, a high-quality singing voice synthesis model.•Propose HiddenSinger-U, an unsupervised learning framework to train with unlabeled datasets.•Audio samples are available at https://jisang93.github.io/hiddensinger-demo/.