# YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidance

arXiv: https://arxiv.org/abs/2512.04779 · HTML: https://mlsanity.com/paper/2512.04779/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 38 of its 43 references that are in the map.
- First posted on arXiv 4 Dec 2025.

## Builds on (most cited first, 30 of 38)

- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Learning to summarize from human feedback](https://mlsanity.com/paper/2009.01325/) (2020)
- [WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing](https://mlsanity.com/paper/2110.13900/) (2021)
- [Flow-GRPO: Training Flow Matching Models via Online RL](https://mlsanity.com/paper/2505.05470/) (2025)
- [DanceGRPO: Unleashing GRPO on Visual Generation](https://mlsanity.com/paper/2505.07818/) (2025)
- [F5-TTS: A Fairytaler that Fakes Fluent and Faithful Speech with Flow Matching](https://mlsanity.com/paper/2410.06885/) (2024)
- [DNSMOS: A Non-Intrusive Perceptual Objective Speech Quality metric to evaluate Noise Suppressors](https://mlsanity.com/paper/2010.15258/) (2020)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [Reliability of CKA as a Similarity Measure in Deep Learning](https://mlsanity.com/paper/2210.16156/) (2022)
- [LongCat-Video Technical Report](https://mlsanity.com/paper/2510.22200/) (2025)
- [Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus](https://mlsanity.com/paper/2112.10358/) (2021)
- [Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis](https://mlsanity.com/paper/2201.07429/) (2022)
- [FireRedASR: Open-Source Industrial-Grade Mandarin Speech Recognition Models from Encoder-Decoder to LLM Integration](https://mlsanity.com/paper/2501.14350/) (2025)
- [DiffRhythm: Blazingly Fast and Embarrassingly Simple End-to-End Full-Length Song Generation with Latent Diffusion](https://mlsanity.com/paper/2503.01183/) (2025)
- [HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis](https://mlsanity.com/paper/2009.01776/) (2020)
- [VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesis](https://mlsanity.com/paper/2110.08813/) (2021)
- [Vevo: Controllable Zero-Shot Voice Imitation with Self-Supervised Disentanglement](https://mlsanity.com/paper/2502.07243/) (2025)
- [XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System](https://mlsanity.com/paper/2006.06261/) (2020)
- [RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Music](https://mlsanity.com/paper/2306.15412/) (2023)
- [GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks](https://mlsanity.com/paper/2409.13832/) (2024)
- [The Singing Voice Conversion Challenge 2023](https://mlsanity.com/paper/2306.14422/) (2023)
- [F5R-TTS: Improving Flow-Matching based Text-to-Speech with Group Relative Policy Optimization](https://mlsanity.com/paper/2504.02407/) (2025)
- [TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control](https://mlsanity.com/paper/2409.15977/) (2024)
- [Reinforcement Learning for Emotional Text-to-Speech Synthesis with Improved Emotion Discriminability](https://mlsanity.com/paper/2104.01408/) (2021)
- [Text-to-Song: Towards Controllable Music Generation Incorporating Vocals and Accompaniment](https://mlsanity.com/paper/2404.09313/) (2024)
- [RMSSinger: Realistic-Music-Score based Singing Voice Synthesis](https://mlsanity.com/paper/2305.10686/) (2023)
- [N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement](https://mlsanity.com/paper/2106.15205/) (2021)

## Built on by (most cited first, 5 of 5)

- [SoulX-Singer: Towards High-Quality Zero-Shot Singing Voice Synthesis](https://mlsanity.com/paper/2602.07803/) (2026)
- [Advances in GRPO for Generation Models: A Survey](https://mlsanity.com/paper/2603.06623/) (2026)
- [TIGFlow-GRPO: Trajectory Forecasting via Interaction-Aware Flow Matching and Reward-Guided Optimization](https://mlsanity.com/paper/2603.24936/) (2026)
- [VocalParse: Towards Unified and Scalable Singing Voice Transcription with Large Audio Language Models](https://mlsanity.com/paper/2605.04613/) (2026)
- [VocalRender: Score-Native Singing Voice Synthesis for Real-World Composition](https://mlsanity.com/paper/2607.27768/) (2026)

## Abstract (arXiv)

Singing Voice Synthesis (SVS) remains constrained in practical deployment due to its strong dependence on accurate phoneme-level alignment and manually annotated melody contours, requirements that are resource-intensive and hinder scalability. To overcome these limitations, we propose a melody-driven SVS framework capable of synthesizing arbitrary lyrics following any reference melody, without relying on phoneme-level alignment. Our method builds on a Diffusion Transformer (DiT) architecture, enhanced with a dedicated melody extraction module that derives melody representations directly from reference audio. To ensure robust melody encoding, we employ a teacher model to guide the optimization of the melody extractor, alongside an implicit alignment mechanism that enforces similarity distribution constraints for improved melodic stability and coherence. Additionally, we refine duration modeling using weakly annotated song data and introduce a Flow-GRPO reinforcement learning strategy with a multi-objective reward function to jointly enhance pronunciation clarity and melodic fidelity. Experiments show that our model achieves superior performance over existing approaches in both objective measures and subjective listening tests, especially in zero-shot and lyric adaptation settings, while maintaining high audio quality without manual annotation. This work offers a practical and scalable solution for advancing data-efficient singing voice synthesis. To support reproducibility, we release our inference code and model checkpoints.