Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909222814351360 |
|---|---|
| author | Shi, Jiatong Lin, Yueqian Bai, Xinyi Zhang, Keyi Wu, Yuning Tang, Yuxun Yu, Yifeng Jin, Qin Watanabe, Shinji |
| author_facet | Shi, Jiatong Lin, Yueqian Bai, Xinyi Zhang, Keyi Wu, Yuning Tang, Yuxun Yu, Yifeng Jin, Qin Watanabe, Shinji |
| contents | In singing voice synthesis (SVS), generating singing voices from musical scores faces challenges due to limited data availability. This study proposes a unique strategy to address the data scarcity in SVS. We employ an existing singing voice synthesizer for data augmentation, complemented by detailed manual tuning, an approach not previously explored in data curation, to reduce instances of unnatural voice synthesis. This innovative method has led to the creation of two expansive singing voice datasets, ACE-Opencpop and ACE-KiSing, which are instrumental for large-scale, multi-singer voice synthesis. Through thorough experimentation, we establish that these datasets not only serve as new benchmarks for SVS but also enhance SVS performance on other singing voice datasets when used as supplementary resources. The corpora, pre-trained models, and their related training recipes are publicly available at ESPnet-Muskits (\url{https://github.com/espnet/espnet}) |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_17619 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing Shi, Jiatong Lin, Yueqian Bai, Xinyi Zhang, Keyi Wu, Yuning Tang, Yuxun Yu, Yifeng Jin, Qin Watanabe, Shinji Sound Audio and Speech Processing In singing voice synthesis (SVS), generating singing voices from musical scores faces challenges due to limited data availability. This study proposes a unique strategy to address the data scarcity in SVS. We employ an existing singing voice synthesizer for data augmentation, complemented by detailed manual tuning, an approach not previously explored in data curation, to reduce instances of unnatural voice synthesis. This innovative method has led to the creation of two expansive singing voice datasets, ACE-Opencpop and ACE-KiSing, which are instrumental for large-scale, multi-singer voice synthesis. Through thorough experimentation, we establish that these datasets not only serve as new benchmarks for SVS but also enhance SVS performance on other singing voice datasets when used as supplementary resources. The corpora, pre-trained models, and their related training recipes are publicly available at ESPnet-Muskits (\url{https://github.com/espnet/espnet}) |
| title | Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2401.17619 |