# MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis

arXiv: https://arxiv.org/abs/2106.07886 · HTML: https://mlsanity.com/paper/2106.07886/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jun 2021.

## Built on by (most cited first, 4 of 4)

- [MLP Architectures for Vision-and-Language Modeling: An Empirical Study](https://mlsanity.com/paper/2112.04453/) (2021)
- [SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategy](https://mlsanity.com/paper/2203.17001/) (2022)
- [MakeSinger: A Semi-Supervised Training Method for Data-Efficient Singing Voice Synthesis via Classifier-free Diffusion Guidance](https://mlsanity.com/paper/2406.05965/) (2024)
- [Melody or Machine: Detecting Synthetic Music with Dual-Stream Contrastive Learning](https://mlsanity.com/paper/2512.00621/) (2025)

## Abstract (arXiv)

Recent developments in deep learning have significantly improved the quality of synthesized singing voice audio. However, prominent neural singing voice synthesis systems suffer from slow inference speed due to their autoregressive design. Inspired by MLP-Mixer, a novel architecture introduced in the vision literature for attention-free image classification, we propose MLP Singer, a parallel Korean singing voice synthesis system. To the best of our knowledge, this is the first work that uses an entirely MLP-based architecture for voice synthesis. Listening tests demonstrate that MLP Singer outperforms a larger autoregressive GAN-based system, both in terms of audio quality and synthesis speed. In particular, MLP Singer achieves a real-time factor of up to 200 and 3400 on CPUs and GPUs respectively, enabling order of magnitude faster generation on both environments.