Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915091242287104 |
|---|---|
| author | Wang, Yongqi Hu, Ruofan Huang, Rongjie Hong, Zhiqing Li, Ruiqi Liu, Wenrui You, Fuming Jin, Tao Zhao, Zhou |
| author_facet | Wang, Yongqi Hu, Ruofan Huang, Rongjie Hong, Zhiqing Li, Ruiqi Liu, Wenrui You, Fuming Jin, Tao Zhao, Zhou |
| contents | Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation that enables text-conditioned vocal range control while keeping melodic accuracy. Furthermore, we explore various experiment settings, including different types of text representations, text encoder fine-tuning, and introducing speech data to alleviate data scarcity, aiming to facilitate further research. Experiments show that our model achieves favorable controlling ability and audio quality. Audio samples are available at http://prompt-singer.github.io . |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_11780 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt Wang, Yongqi Hu, Ruofan Huang, Rongjie Hong, Zhiqing Li, Ruiqi Liu, Wenrui You, Fuming Jin, Tao Zhao, Zhou Sound Artificial Intelligence Machine Learning Audio and Speech Processing Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation that enables text-conditioned vocal range control while keeping melodic accuracy. Furthermore, we explore various experiment settings, including different types of text representations, text encoder fine-tuning, and introducing speech data to alleviate data scarcity, aiming to facilitate further research. Experiments show that our model achieves favorable controlling ability and audio quality. Audio samples are available at http://prompt-singer.github.io . |
| title | Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt |
| topic | Sound Artificial Intelligence Machine Learning Audio and Speech Processing |
| url | https://arxiv.org/abs/2403.11780 |