Zero-Shot Sing Voice Conversion: built upon clustering-based phoneme representations

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Wangjin, Zhang, Fengrun, Liu, Yiming, Guan, Wenhao, Zhao, Yi, Kawahara, Tatsuya
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929539947429888
author Zhou, Wangjin
Zhang, Fengrun
Liu, Yiming
Guan, Wenhao
Zhao, Yi
Kawahara, Tatsuya
author_facet Zhou, Wangjin
Zhang, Fengrun
Liu, Yiming
Guan, Wenhao
Zhao, Yi
Kawahara, Tatsuya
contents This study presents an innovative Zero-Shot any-to-any Singing Voice Conversion (SVC) method, leveraging a novel clustering-based phoneme representation to effectively separate content, timbre, and singing style. This approach enables precise voice characteristic manipulation. We discovered that datasets with fewer recordings per artist are more susceptible to timbre leakage. Extensive testing on over 10,000 hours of singing and user feedback revealed our model significantly improves sound quality and timbre accuracy, aligning with our objectives and advancing voice conversion technology. Furthermore, this research advances zero-shot SVC and sets the stage for future work on discrete speech representation, emphasizing the preservation of rhyme.
format Preprint
id arxiv_https___arxiv_org_abs_2409_08039
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Zero-Shot Sing Voice Conversion: built upon clustering-based phoneme representations
Zhou, Wangjin
Zhang, Fengrun
Liu, Yiming
Guan, Wenhao
Zhao, Yi
Kawahara, Tatsuya
Sound
Audio and Speech Processing
This study presents an innovative Zero-Shot any-to-any Singing Voice Conversion (SVC) method, leveraging a novel clustering-based phoneme representation to effectively separate content, timbre, and singing style. This approach enables precise voice characteristic manipulation. We discovered that datasets with fewer recordings per artist are more susceptible to timbre leakage. Extensive testing on over 10,000 hours of singing and user feedback revealed our model significantly improves sound quality and timbre accuracy, aligning with our objectives and advancing voice conversion technology. Furthermore, this research advances zero-shot SVC and sets the stage for future work on discrete speech representation, emphasizing the preservation of rhyme.
title Zero-Shot Sing Voice Conversion: built upon clustering-based phoneme representations
topic Sound
Audio and Speech Processing
url https://arxiv.org/abs/2409.08039