SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911912310079488 |
|---|---|
| author | Bai, Bingsong Wang, Fengping Gao, Yingming Li, Ya |
| author_facet | Bai, Bingsong Wang, Fengping Gao, Yingming Li, Ya |
| contents | Diffusion-based singing voice conversion (SVC) models have shown better synthesis quality compared to traditional methods. However, in cross-domain SVC scenarios, where there is a significant disparity in pitch between the source and target voice domains, the models tend to generate audios with hoarseness, posing challenges in achieving high-quality vocal outputs. Therefore, in this paper, we propose a Self-supervised Pitch Augmentation method for Singing Voice Conversion (SPA-SVC), which can enhance the voice quality in SVC tasks without requiring additional data or increasing model parameters. We innovatively introduce a cycle pitch shifting training strategy and Structural Similarity Index (SSIM) loss into our SVC model, effectively enhancing its performance. Experimental results on the public singing datasets M4Singer indicate that our proposed method significantly improves model performance in both general SVC scenarios and particularly in cross-domain SVC scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_05692 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion Bai, Bingsong Wang, Fengping Gao, Yingming Li, Ya Sound Artificial Intelligence Audio and Speech Processing Diffusion-based singing voice conversion (SVC) models have shown better synthesis quality compared to traditional methods. However, in cross-domain SVC scenarios, where there is a significant disparity in pitch between the source and target voice domains, the models tend to generate audios with hoarseness, posing challenges in achieving high-quality vocal outputs. Therefore, in this paper, we propose a Self-supervised Pitch Augmentation method for Singing Voice Conversion (SPA-SVC), which can enhance the voice quality in SVC tasks without requiring additional data or increasing model parameters. We innovatively introduce a cycle pitch shifting training strategy and Structural Similarity Index (SSIM) loss into our SVC model, effectively enhancing its performance. Experimental results on the public singing datasets M4Singer indicate that our proposed method significantly improves model performance in both general SVC scenarios and particularly in cross-domain SVC scenarios. |
| title | SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion |
| topic | Sound Artificial Intelligence Audio and Speech Processing |
| url | https://arxiv.org/abs/2406.05692 |