# SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategy

arXiv: https://arxiv.org/abs/2203.17001 · HTML: https://mlsanity.com/paper/2203.17001/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 32 of its 43 references that are in the map.
- First posted on arXiv 31 Mar 2022.

## Builds on (most cited first, 30 of 32)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [AdvAug: Robust Adversarial Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2006.11834/) (2020)
- [Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesis](https://mlsanity.com/paper/2201.07429/) (2022)
- [Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens](https://mlsanity.com/paper/1910.11997/) (2019)
- [HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis](https://mlsanity.com/paper/2009.01776/) (2020)
- [MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition](https://mlsanity.com/paper/2102.12664/) (2021)
- [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)
- [DeepSinger: Singing Voice Synthesis with Data Mined From the Web](https://mlsanity.com/paper/2007.04590/) (2020)
- [Low-resource expressive text-to-speech using data augmentation](https://mlsanity.com/paper/2011.05707/) (2020)
- [Adversarially Trained End-to-end Korean Singing Voice Synthesis System](https://mlsanity.com/paper/1908.01919/) (2019)
- [ByteSing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoders](https://mlsanity.com/paper/2004.11012/) (2020)
- [Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformer](https://mlsanity.com/paper/1910.09989/) (2019)
- [TTS-by-TTS: TTS-driven Data Augmentation for Fast and High-Quality Speech Synthesis](https://mlsanity.com/paper/2010.13421/) (2020)
- [A Neural Parametric Singing Synthesizer](https://mlsanity.com/paper/1704.03809/) (2017)
- [DurIAN-SC: Duration Informed Attention Network based Singing Voice Conversion System](https://mlsanity.com/paper/2008.03009/) (2020)
- [WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN](https://mlsanity.com/paper/1903.10729/) (2019)
- [Adversarially Trained Multi-Singer Sequence-To-Sequence Singing Synthesizer](https://mlsanity.com/paper/2006.10317/) (2020)
- [Singing voice synthesis based on convolutional neural networks](https://mlsanity.com/paper/1904.06868/) (2019)
- [Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modeling](https://mlsanity.com/paper/1906.08977/) (2019)
- [Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks](https://mlsanity.com/paper/1910.11690/) (2019)
- [Mel-spectrogram augmentation for sequence to sequence voice conversion](https://mlsanity.com/paper/2001.01401/) (2020)
- [WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses](https://mlsanity.com/paper/2203.10750/) (2022)
- [Sequence-to-sequence Singing Voice Synthesis with Perceptual Entropy Loss](https://mlsanity.com/paper/2010.12024/) (2020)
- [PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcription](https://mlsanity.com/paper/2109.07940/) (2021)
- [Score and Lyrics-Free Singing Voice Generation](https://mlsanity.com/paper/1912.11747/) (2019)
- [MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis](https://mlsanity.com/paper/2106.07886/) (2021)

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

- [SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion](https://mlsanity.com/paper/2406.05692/) (2024)
- [CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidance](https://mlsanity.com/paper/2509.19883/) (2025)
- [Unsupervised Pre-Training For Data-Efficient Text-to-Speech On Low Resource Languages](https://mlsanity.com/paper/2303.15669/) (2023)

## Abstract (arXiv)

Deep learning based singing voice synthesis (SVS) systems have been demonstrated to flexibly generate singing with better qualities, compared to conventional statistical parametric based methods. However, neural systems are generally data-hungry and have difficulty to reach reasonable singing quality with limited public available training data. In this work, we explore different data augmentation methods to boost the training of SVS systems, including several strategies customized to SVS based on pitch augmentation and mix-up augmentation. To further stabilize the training, we introduce the cycle-consistent training strategy. Extensive experiments on two public singing databases demonstrate that our proposed augmentation methods and the stabilizing training strategy can significantly improve the performance on both objective and subjective evaluations.