Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion

Ruiqi Li, Rongjie Huang, Yongqi Wang, Zhiqing Hong, Zhou Zhao


Abstract
Speech-to-singing voice conversion (STS) task always suffers from data scarcity, because it requires paired speech and singing data. Compounding this issue are the challenges of content-pitch alignment and the suboptimal quality of generated outputs, presenting significant hurdles in STS research. This paper presents SVPT, an STS approach boosted by a self-supervised singing voice pre-training model.We leverage spoken language model techniques to tackle the rhythm alignment problem and the in-context learning capability to achieve zero-shot conversion. We adopt discrete-unit random resampling and pitch corruption strategies, enabling training with unpaired singing data and thus mitigating the issue of data scarcity. SVPT also serves as an effective backbone for singing voice synthesis (SVS), offering insights into scaling up SVS models. Experimental results indicate that SVPT delivers notable improvements in both STS and SVS endeavors. Audio samples are available at https://speech2sing.github.io.
Anthology ID:
2024.findings-acl.585
Volume:
Findings of the Association for Computational Linguistics ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand and virtual meeting
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9819–9831
Language:
URL:
https://aclanthology.org/2024.findings-acl.585
DOI:
Bibkey:
Cite (ACL):
Ruiqi Li, Rongjie Huang, Yongqi Wang, Zhiqing Hong, and Zhou Zhao. 2024. Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion. In Findings of the Association for Computational Linguistics ACL 2024, pages 9819–9831, Bangkok, Thailand and virtual meeting. Association for Computational Linguistics.
Cite (Informal):
Self-Supervised Singing Voice Pre-Training towards Speech-to-Singing Conversion (Li et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.findings-acl.585.pdf