YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908948952514560 |
|---|---|
| author | Hao, Chunbo Zheng, Junjie Ma, Guobin Jiang, Yuepeng Chen, Huakang Tian, Wenjie Chen, Gongyu Chen, Zihao Xie, Lei |
| author_facet | Hao, Chunbo Zheng, Junjie Ma, Guobin Jiang, Yuepeng Chen, Huakang Tian, Wenjie Chen, Gongyu Chen, Zihao Xie, Lei |
| contents | Regenerating singing voices with altered lyrics while preserving melody consistency remains challenging, as existing methods either offer limited controllability or require laborious manual alignment. We propose YingMusic-Singer-Plus, a fully diffusion-based model enabling melody-controllable singing voice synthesis with flexible lyric manipulation. The model takes three inputs: an optional timbre reference, a melody-providing singing clip, and modified lyrics, without manual alignment. Trained with curriculum learning and Group Relative Policy Optimization, YingMusic-Singer-Plus achieves stronger melody preservation and lyric adherence than Vevo2, the most comparable baseline supporting melody control without manual alignment. We also introduce LyricEditBench, the first benchmark for melody-preserving lyric modification evaluation. The code, weights, benchmark, and demos are publicly available at https://github.com/ASLP-lab/YingMusic-Singer-Plus. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_24589 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance Hao, Chunbo Zheng, Junjie Ma, Guobin Jiang, Yuepeng Chen, Huakang Tian, Wenjie Chen, Gongyu Chen, Zihao Xie, Lei Audio and Speech Processing Sound Regenerating singing voices with altered lyrics while preserving melody consistency remains challenging, as existing methods either offer limited controllability or require laborious manual alignment. We propose YingMusic-Singer-Plus, a fully diffusion-based model enabling melody-controllable singing voice synthesis with flexible lyric manipulation. The model takes three inputs: an optional timbre reference, a melody-providing singing clip, and modified lyrics, without manual alignment. Trained with curriculum learning and Group Relative Policy Optimization, YingMusic-Singer-Plus achieves stronger melody preservation and lyric adherence than Vevo2, the most comparable baseline supporting melody control without manual alignment. We also introduce LyricEditBench, the first benchmark for melody-preserving lyric modification evaluation. The code, weights, benchmark, and demos are publicly available at https://github.com/ASLP-lab/YingMusic-Singer-Plus. |
| title | YingMusic-Singer-Plus: Controllable Singing Voice Synthesis with Flexible Lyric Manipulation and Annotation-free Melody Guidance |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2603.24589 |