ConSinger: Efficient High-Fidelity Singing Voice Generation with Minimal Steps

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Song, Yulin, Sang, Guorui, Yu, Jing, Xiao, Chuangbai
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912263167803392
author Song, Yulin
Sang, Guorui
Yu, Jing
Xiao, Chuangbai
author_facet Song, Yulin
Sang, Guorui
Yu, Jing
Xiao, Chuangbai
contents Singing voice synthesis (SVS) system is expected to generate high-fidelity singing voice from given music scores (lyrics, duration and pitch). Recently, diffusion models have performed well in this field. However, sacrificing inference speed to exchange with high-quality sample generation limits its application scenarios. In order to obtain high quality synthetic singing voice more efficiently, we propose a singing voice synthesis method based on the consistency model, ConSinger, to achieve high-fidelity singing voice synthesis with minimal steps. The model is trained by applying consistency constraint and the generation quality is greatly improved at the expense of a small amount of inference speed. Our experiments show that ConSinger is highly competitive with the baseline model in terms of generation speed and quality. Audio samples are available at https://keylxiao.github.io/consinger.
format Preprint
id arxiv_https___arxiv_org_abs_2410_15342
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle ConSinger: Efficient High-Fidelity Singing Voice Generation with Minimal Steps
Song, Yulin
Sang, Guorui
Yu, Jing
Xiao, Chuangbai
Sound
Machine Learning
Audio and Speech Processing
Singing voice synthesis (SVS) system is expected to generate high-fidelity singing voice from given music scores (lyrics, duration and pitch). Recently, diffusion models have performed well in this field. However, sacrificing inference speed to exchange with high-quality sample generation limits its application scenarios. In order to obtain high quality synthetic singing voice more efficiently, we propose a singing voice synthesis method based on the consistency model, ConSinger, to achieve high-fidelity singing voice synthesis with minimal steps. The model is trained by applying consistency constraint and the generation quality is greatly improved at the expense of a small amount of inference speed. Our experiments show that ConSinger is highly competitive with the baseline model in terms of generation speed and quality. Audio samples are available at https://keylxiao.github.io/consinger.
title ConSinger: Efficient High-Fidelity Singing Voice Generation with Minimal Steps
topic Sound
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2410.15342