# Sequence-to-sequence Singing Voice Synthesis with Perceptual Entropy Loss

arXiv: https://arxiv.org/abs/2010.12024 · HTML: https://mlsanity.com/paper/2010.12024/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Oct 2020.

## Built on by (most cited first, 6 of 6)

- [Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System](https://mlsanity.com/paper/2108.02776/) (2021)
- [SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessment](https://mlsanity.com/paper/2510.01812/) (2025)
- [SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategy](https://mlsanity.com/paper/2203.17001/) (2022)
- [NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit](https://mlsanity.com/paper/2210.15987/) (2022)
- [Singing Voice Synthesis Based on a Musical Note Position-Aware Attention Mechanism](https://mlsanity.com/paper/2212.13703/) (2022)
- [Singing voice synthesis based on frame-level sequence-to-sequence models considering vocal timing deviation](https://mlsanity.com/paper/2301.02262/) (2023)

## Abstract (arXiv)

The neural network (NN) based singing voice synthesis (SVS) systems require sufficient data to train well and are prone to over-fitting due to data scarcity. However, we often encounter data limitation problem in building SVS systems because of high data acquisition and annotation costs. In this work, we propose a Perceptual Entropy (PE) loss derived from a psycho-acoustic hearing model to regularize the network. With a one-hour open-source singing voice database, we explore the impact of the PE loss on various mainstream sequence-to-sequence models, including the RNN-based, transformer-based, and conformer-based models. Our experiments show that the PE loss can mitigate the over-fitting problem and significantly improve the synthesized singing quality reflected in objective and subjective evaluations.