mlsanityData to 7 Oct 2026

SPA-SVC: Self-supervised Pitch Augmentation for Singing Voice Conversion

arXiv 2406.05692 ↗First posted 9 Jun 2024cs.SD cs.AI eess.AScited by 3

Not on the map. Why?

Abstract (arXiv)

Diffusion-based singing voice conversion (SVC) models have shown better synthesis quality compared to traditional methods. However, in cross-domain SVC scenarios, where there is a significant disparity in pitch between the source and target voice domains, the models tend to generate audios with hoarseness, posing challenges in achieving high-quality vocal outputs. Therefore, in this paper, we propose a Self-supervised Pitch Augmentation method for Singing Voice Conversion (SPA-SVC), which can enhance the voice quality in SVC tasks without requiring additional data or increasing model parameters. We innovatively introduce a cycle pitch shifting training strategy and Structural Similarity Index (SSIM) loss into our SVC model, effectively enhancing its performance. Experimental results on the public singing datasets M4Singer indicate that our proposed method significantly improves model performance in both general SVC scenarios and particularly in cross-domain SVC scenarios.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 20 of its 27 references that are in the map. First posted on arXiv 9 Jun 2024.

Builds on

20 of 27 references.

References · 20

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2020wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representationscited by 3,853
  3. 2021HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Unitscited by 2,301
  4. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  5. 2021WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processingcited by 1,609
  6. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  7. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  8. 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 555
  9. 2020DDSP: Differentiable Digital Signal Processingcited by 177
  10. 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
  11. 2022ContentVec: An Improved Self-Supervised Speech Representation by Disentangling Speakerscited by 73
  12. 2021DiffSVC: A Diffusion Probabilistic Model for Singing Voice Conversioncited by 39
8 more
  1. 2022VoiceFixer: A Unified Framework for High-Fidelity Speech Restorationcited by 37
  2. 2023RMVPE: A Robust Model for Vocal Pitch Estimation in Polyphonic Musiccited by 27
  3. 2018Neural source-filter-based waveform model for statistical parametric speech synthesiscited by 21
  4. 2020FastSVC: Fast Cross-Domain Singing Voice Conversion with Feature-wise Linear Modulationcited by 21
  5. 2024CoMoSVC: Consistency Model-based Singing Voice Conversioncited by 11
  6. 2023VITS-based Singing Voice Conversion System with DSPGAN post-processing for SVCC2023cited by 5
  7. 2022SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategycited by 3
  8. 2023MBTFNet: Multi-Band Temporal-Frequency Neural Network For Singing Voice Enhancementcited by 1

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025DAFMSVC: One-Shot Singing Voice Conversion with Dual Attention Mechanism and Flow Matchingcited by 2
  2. 2025YingMusic-SVC: Real-World Robust Zero-Shot Singing Voice Conversion with Flow-GRPO and Singing-Specific Inductive Biasescited by 2
  3. 2025VibE-SVC: Vibrato Extraction with High-frequency F0 Contour for Singing Voice Conversioncited by 1