Problem
Research questions and friction points this paper is trying to address.
Singing Voice Beautifying
Style-Consistent
Pitch and Rhythm Correction
SRF-SVB: Style-Consistent Singing Voice Beautifying via Rectified Flow
🤖 AI Summary
本文提出SRF-SVB模型，通过矫正流实现音高和节奏修正，同时保持歌手风格，解决了现有方法生成质量低、效率差且忽视歌手风格的问题。
📝 Abstract
Singing voice beautifying (SVB) aims to correct pitch and rhythm of amateur singing while enhancing vocal quality, preserving lyrics and the singer's timbre. Existing methods, however, suffer from limited generation quality and efficiency, and tend to neglect the preservation of the singer's style. We propose SRF-SVB, a style-consistent model for SVB via rectified flow, which achieves high-fidelity and efficient beautification covering pitch and rhythm correction. Furthermore, we design a context-guided masked mel-spectrogram inpainting mechanism that effectively preserves the amateur singer's style, including unique timbre and expressive patterns. Experiments on both English and Chinese test sets show that SRF-SVB outperforms baseline models in most objective and subjective metrics.
Innovation
Methods, ideas, or system contributions that make the work stand out.
style-consistent
rectified flow
masked mel-spectrogram inpainting
🔎 Similar Papers
No similar papers found.
