SingVERSE: A Diverse, Real-World Benchmark for Singing Voice Enhancement

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Jiang, Shaohan, Zhang, Junan, Zhang, Yunjia, Yang, Jing, Fan, Fan, Wu, Zhizheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912604661743616
author Jiang, Shaohan
Zhang, Junan
Zhang, Yunjia
Yang, Jing
Fan, Fan
Wu, Zhizheng
author_facet Jiang, Shaohan
Zhang, Junan
Zhang, Yunjia
Yang, Jing
Fan, Fan
Wu, Zhizheng
contents This paper presents a benchmark for singing voice enhancement. The development of singing voice enhancement is limited by the lack of realistic evaluation data. To address this gap, this paper introduces SingVERSE, the first real-world benchmark for singing voice enhancement, covering diverse acoustic scenarios and providing paired, studio-quality clean references. Leveraging SingVERSE, we conduct a comprehensive evaluation of state-of-the-art models and uncover a consistent trade-off between perceptual quality and intelligibility. Finally, we show that training on in-domain singing data substantially improves enhancement performance without degrading speech capabilities, establishing a simple yet effective path forward. This work offers the community a foundational benchmark together with critical insights to guide future advances in this underexplored domain. Demopage: https://singverse.github.io
format Preprint
id arxiv_https___arxiv_org_abs_2509_20969
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SingVERSE: A Diverse, Real-World Benchmark for Singing Voice Enhancement
Jiang, Shaohan
Zhang, Junan
Zhang, Yunjia
Yang, Jing
Fan, Fan
Wu, Zhizheng
Sound
Audio and Speech Processing
This paper presents a benchmark for singing voice enhancement. The development of singing voice enhancement is limited by the lack of realistic evaluation data. To address this gap, this paper introduces SingVERSE, the first real-world benchmark for singing voice enhancement, covering diverse acoustic scenarios and providing paired, studio-quality clean references. Leveraging SingVERSE, we conduct a comprehensive evaluation of state-of-the-art models and uncover a consistent trade-off between perceptual quality and intelligibility. Finally, we show that training on in-domain singing data substantially improves enhancement performance without degrading speech capabilities, establishing a simple yet effective path forward. This work offers the community a foundational benchmark together with critical insights to guide future advances in this underexplored domain. Demopage: https://singverse.github.io
title SingVERSE: A Diverse, Real-World Benchmark for Singing Voice Enhancement
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2509.20969