mlsanityData to 7 Oct 2026

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

arXiv 2203.17001 ↗First posted 31 Mar 2022eess.AS cs.LG cs.SDcited by 3

Not on the map. Why?

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 31 Mar 2022.

Builds on

32 of 43 references.

References · 32

  1. 2017Attention Is All You Needcited by 59,932
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  4. 2017Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictionscited by 800
  5. 2020AdvAug: Robust Adversarial Augmentation for Neural Machine Translationcited by 66
  6. 2022Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesiscited by 53
  7. 2019Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokenscited by 44
  8. 2020HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesiscited by 39
  9. 2021MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognitioncited by 38
  10. 2021VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesiscited by 38
  11. 2020XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis Systemcited by 33
  12. 2020DeepSinger: Singing Voice Synthesis with Data Mined From the Webcited by 32
20 more
  1. 2020Low-resource expressive text-to-speech using data augmentationcited by 26
  2. 2019Adversarially Trained End-to-end Korean Singing Voice Synthesis Systemcited by 22
  3. 2020ByteSing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoderscited by 21
  4. 2019Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformercited by 17
  5. 2020TTS-by-TTS: TTS-driven Data Augmentation for Fast and High-Quality Speech Synthesiscited by 15
  6. 2017A Neural Parametric Singing Synthesizercited by 14
  7. 2020DurIAN-SC: Duration Informed Attention Network based Singing Voice Conversion Systemcited by 14
  8. 2019WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GANcited by 13
  9. 2020Adversarially Trained Multi-Singer Sequence-To-Sequence Singing Synthesizercited by 12
  10. 2019Singing voice synthesis based on convolutional neural networkscited by 7
  11. 2019Singing Voice Synthesis Using Deep Autoregressive Neural Networks for Acoustic Modelingcited by 7
  12. 2019Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networkscited by 7
  13. 2020Mel-spectrogram augmentation for sequence to sequence voice conversioncited by 7
  14. 2022WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Lossescited by 7
  15. 2020Sequence-to-sequence Singing Voice Synthesis with Perceptual Entropy Losscited by 6
  16. 2021PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics Transcriptioncited by 5
  17. 2019Score and Lyrics-Free Singing Voice Generationcited by 4
  18. 2021MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesiscited by 4
  19. 2019Learning Singing From Speechcited by 1
  20. 2020Peking Opera Synthesis via Duration Informed Attention Networkcited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 1; 2025: 1.

3 papers.

  1. 2024SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversioncited by 3
  2. 2025CoMelSinger: Discrete Token-Based Zero-Shot Singing Synthesis With Structured Melody Control and Guidancecited by 3
  3. 2023Unsupervised Pre-Training For Data-Efficient Text-to-Speech On Low Resource Languagescited by 1