HQ-SVC: Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Bai, Bingsong, Geng, Yizhong, Wang, Fengping, Wang, Cong, Guo, Puyuan, Gao, Yingming, Li, Ya
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911267696934912
author Bai, Bingsong
Geng, Yizhong
Wang, Fengping
Wang, Cong
Guo, Puyuan
Gao, Yingming
Li, Ya
author_facet Bai, Bingsong
Geng, Yizhong
Wang, Fengping
Wang, Cong
Guo, Puyuan
Gao, Yingming
Li, Ya
contents Zero-shot singing voice conversion (SVC) transforms a source singer's timbre to an unseen target speaker's voice while preserving melodic content without fine-tuning. Existing methods model speaker timbre and vocal content separately, losing essential acoustic information that degrades output quality while requiring significant computational resources. To overcome these limitations, we propose HQ-SVC, an efficient framework for high-quality zero-shot SVC. HQ-SVC first extracts jointly content and speaker features using a decoupled codec. It then enhances fidelity through pitch and volume modeling, preserving critical acoustic information typically lost in separate modeling approaches, and progressively refines outputs via differentiable signal processing and diffusion techniques. Evaluations confirm HQ-SVC significantly outperforms state-of-the-art zero-shot SVC methods in conversion quality and efficiency. Beyond voice conversion, HQ-SVC achieves superior voice naturalness compared to specialized audio super-resolution methods while natively supporting voice super-resolution tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08496
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HQ-SVC: Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios
Bai, Bingsong
Geng, Yizhong
Wang, Fengping
Wang, Cong
Guo, Puyuan
Gao, Yingming
Li, Ya
Sound
Artificial Intelligence
Audio and Speech Processing
Zero-shot singing voice conversion (SVC) transforms a source singer's timbre to an unseen target speaker's voice while preserving melodic content without fine-tuning. Existing methods model speaker timbre and vocal content separately, losing essential acoustic information that degrades output quality while requiring significant computational resources. To overcome these limitations, we propose HQ-SVC, an efficient framework for high-quality zero-shot SVC. HQ-SVC first extracts jointly content and speaker features using a decoupled codec. It then enhances fidelity through pitch and volume modeling, preserving critical acoustic information typically lost in separate modeling approaches, and progressively refines outputs via differentiable signal processing and diffusion techniques. Evaluations confirm HQ-SVC significantly outperforms state-of-the-art zero-shot SVC methods in conversion quality and efficiency. Beyond voice conversion, HQ-SVC achieves superior voice naturalness compared to specialized audio super-resolution methods while natively supporting voice super-resolution tasks.
title HQ-SVC: Towards High-Quality Zero-Shot Singing Voice Conversion in Low-Resource Scenarios
topic Sound
Artificial Intelligence
Audio and Speech Processing
url https://arxiv.org/abs/2511.08496