# Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GAN

arXiv: https://arxiv.org/abs/2209.10446 · HTML: https://mlsanity.com/paper/2209.10446/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Audio, speech and music, one of 14 directions in Diffusion models.
- Builds on 26 of its 42 references that are in the map.
- First posted on arXiv 21 Sep 2022.

## Placed in

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

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [Score-Based Generative Modeling through Stochastic Differential Equations](https://mlsanity.com/paper/2011.13456/) (2020)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning](https://mlsanity.com/paper/1702.03118/) (2017)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [Wasserstein GAN](https://mlsanity.com/paper/1701.07875/) (2017)
- [Tackling the Generative Learning Trilemma with Denoising Diffusion GANs](https://mlsanity.com/paper/2112.07804/) (2021)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [Diff-TTS: A Denoising Diffusion Model for Text-to-Speech](https://mlsanity.com/paper/2104.01409/) (2021)
- [Conditional Diffusion Probabilistic Model for Speech Enhancement](https://mlsanity.com/paper/2202.05256/) (2022)
- [High Fidelity Speech Synthesis with Adversarial Networks](https://mlsanity.com/paper/1909.11646/) (2019)
- [DiffGAN-TTS: High-Fidelity and Efficient Text-to-Speech with Denoising Diffusion GANs](https://mlsanity.com/paper/2201.11972/) (2022)
- [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)
- [XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System](https://mlsanity.com/paper/2006.06261/) (2020)
- [Wasserstein Divergence for GANs](https://mlsanity.com/paper/1712.01026/) (2017)
- [Adversarially Trained End-to-end Korean Singing Voice Synthesis System](https://mlsanity.com/paper/1908.01919/) (2019)
- [Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer](https://mlsanity.com/paper/1910.09989/) (2019)
- [DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive Evaluation](https://mlsanity.com/paper/2208.04756/) (2022)

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

- [TransFusion: Generating Long, High Fidelity Time Series using Diffusion Models with Transformers](https://mlsanity.com/paper/2307.12667/) (2023)
- [TCSinger 2: Customizable Multilingual Zero-shot Singing Voice Synthesis](https://mlsanity.com/paper/2505.14910/) (2025)
- [Agent-Driven Large Language Models for Mandarin Lyric Generation](https://mlsanity.com/paper/2410.01450/) (2024)
- [Singing voice synthesis based on frame-level sequence-to-sequence models considering vocal timing deviation](https://mlsanity.com/paper/2301.02262/) (2023)
- [ConSinger: Efficient High-Fidelity Singing Voice Generation with Minimal Steps](https://mlsanity.com/paper/2410.15342/) (2024)

## Abstract (arXiv)

Singing voice synthesis (SVS) is the computer production of a human-like singing voice from given musical scores. To accomplish end-to-end SVS effectively and efficiently, this work adopts the acoustic model-neural vocoder architecture established for high-quality speech and singing voice synthesis. Specifically, this work aims to pursue a higher level of expressiveness in synthesized voices by combining the diffusion denoising probabilistic model (DDPM) and Wasserstein generative adversarial network (WGAN) to construct the backbone of the acoustic model. On top of the proposed acoustic model, a HiFi-GAN neural vocoder is adopted with integrated fine-tuning to ensure optimal synthesis quality for the resulting end-to-end SVS system. This end-to-end system was evaluated with the multi-singer Mpop600 Mandarin singing voice dataset. In the experiments, the proposed system exhibits improvements over previous landmark counterparts in terms of musical expressiveness and high-frequency acoustic details. Moreover, the adversarial acoustic model converged stably without the need to enforce reconstruction objectives, indicating the convergence stability of the proposed DDPM and WGAN combined architecture over alternative GAN-based SVS systems.