# ConSinger: Efficient High-Fidelity Singing Voice Generation with Minimal Steps

arXiv: https://arxiv.org/abs/2410.15342 · HTML: https://mlsanity.com/paper/2410.15342/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 20 Oct 2024.

## Builds on (most cited first, 22 of 22)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [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)
- [Generative Modeling by Estimating Gradients of the Data Distribution](https://mlsanity.com/paper/1907.05600/) (2019)
- [Elucidating the Design Space of Diffusion-Based Generative Models](https://mlsanity.com/paper/2206.00364/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [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)
- [FastSpeech 2: Fast and High-Quality End-to-End Text to Speech](https://mlsanity.com/paper/2006.04558/) (2020)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [VideoLCM: Video Latent Consistency Model](https://mlsanity.com/paper/2312.09109/) (2023)
- [DITTO: Diffusion Inference-Time T-Optimization for Music Generation](https://mlsanity.com/paper/2401.12179/) (2024)
- [A Wavenet for Speech Denoising](https://mlsanity.com/paper/1706.07162/) (2017)
- [CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model](https://mlsanity.com/paper/2305.06908/) (2023)
- [HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis](https://mlsanity.com/paper/2009.01776/) (2020)
- [DeepSinger: Singing Voice Synthesis with Data Mined From the Web](https://mlsanity.com/paper/2007.04590/) (2020)
- [Amphion: An Open-Source Audio, Music and Speech Generation Toolkit](https://mlsanity.com/paper/2312.09911/) (2023)
- [Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer](https://mlsanity.com/paper/1910.09989/) (2019)
- [CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Models](https://mlsanity.com/paper/2404.00569/) (2024)
- [RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses](https://mlsanity.com/paper/2111.00962/) (2021)
- [Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GAN](https://mlsanity.com/paper/2209.10446/) (2022)

## Abstract (arXiv)

Singing voice synthesis (SVS) system is expected to generate high-fidelity singing voice from given music scores (lyrics, duration and pitch). Recently, diffusion models have performed well in this field. However, sacrificing inference speed to exchange with high-quality sample generation limits its application scenarios. In order to obtain high quality synthetic singing voice more efficiently, we propose a singing voice synthesis method based on the consistency model, ConSinger, to achieve high-fidelity singing voice synthesis with minimal steps. The model is trained by applying consistency constraint and the generation quality is greatly improved at the expense of a small amount of inference speed. Our experiments show that ConSinger is highly competitive with the baseline model in terms of generation speed and quality. Audio samples are available at https://keylxiao.github.io/consinger.