# DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment

arXiv: https://arxiv.org/abs/2510.09016 · HTML: https://mlsanity.com/paper/2510.09016/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 16 of its 21 references that are in the map.
- First posted on arXiv 10 Oct 2025.

## Placed in

- Diffusion models / [Audio, speech and music](https://mlsanity.com/diffusion/audio-speech-and-music/)

## Builds on (most cited first, 16 of 16)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps](https://mlsanity.com/paper/2206.00927/) (2022)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [SoundStream: An End-to-End Neural Audio Codec](https://mlsanity.com/paper/2107.03312/) (2021)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System](https://mlsanity.com/paper/2006.06261/) (2020)
- [DeepSinger: Singing Voice Synthesis with Data Mined From the Web](https://mlsanity.com/paper/2007.04590/) (2020)
- [GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks](https://mlsanity.com/paper/2409.13832/) (2024)
- [StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis](https://mlsanity.com/paper/2312.10741/) (2023)
- [A Review of Differentiable Digital Signal Processing for Music & Speech Synthesis](https://mlsanity.com/paper/2308.15422/) (2023)
- [TCSinger: Zero-Shot Singing Voice Synthesis with Style Transfer and Multi-Level Style Control](https://mlsanity.com/paper/2409.15977/) (2024)
- [TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching](https://mlsanity.com/paper/2502.12572/) (2025)
- [RMSSinger: Realistic-Music-Score based Singing Voice Synthesis](https://mlsanity.com/paper/2305.10686/) (2023)

## Built on by (most cited first, 3 of 3)

- [Systematizing LLM Persona Design: A Four-Quadrant Technical Taxonomy for AI Companion Applications](https://mlsanity.com/paper/2511.02979/) (2025)
- [UniVoice: A Unified Model for Speech and Singing Voice Generation](https://mlsanity.com/paper/2606.05852/) (2026)
- [VocalRender: Score-Native Singing Voice Synthesis for Real-World Composition](https://mlsanity.com/paper/2607.27768/) (2026)

## Abstract (arXiv)

Recent progress in diffusion-based Singing Voice Synthesis (SVS) demonstrates strong expressiveness but remains limited by data scarcity and model scalability. We introduce a two-stage pipeline: a compact seed set of human-sung recordings is constructed by pairing fixed melodies with diverse LLM-generated lyrics, and melody-specific models are trained to synthesize over 500 hours of high-quality Chinese singing data. Building on this corpus, we propose DiTSinger, a Diffusion Transformer with RoPE and qk-norm, systematically scaled in depth, width, and resolution for enhanced fidelity. Furthermore, we design an implicit alignment mechanism that obviates phoneme-level duration labels by constraining phoneme-to-acoustic attention within character-level spans, thereby improving robustness under noisy or uncertain alignments. Extensive experiments validate that our approach enables scalable, alignment-free, and high-fidelity SVS.