mlsanityData to 7 Oct 2026

ConSinger: Efficient High-Fidelity Singing Voice Generation with Minimal Steps

arXiv 2410.15342 ↗First posted 20 Oct 2024cs.SD cs.LG eess.AScited by 0

Not on the map. Why?

Abstract (arXiv)

Singing voice synthesis (SVS) system is expected to generate high-fidelity singing voice from given music scores (lyrics, duration and pitch). Recently, diffusion models have performed well in this field. However, sacrificing inference speed to exchange with high-quality sample generation limits its application scenarios. In order to obtain high quality synthetic singing voice more efficiently, we propose a singing voice synthesis method based on the consistency model, ConSinger, to achieve high-fidelity singing voice synthesis with minimal steps. The model is trained by applying consistency constraint and the generation quality is greatly improved at the expense of a small amount of inference speed. Our experiments show that ConSinger is highly competitive with the baseline model in terms of generation speed and quality. Audio samples are available at https://keylxiao.github.io/consinger.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 30 references that are in the map. First posted on arXiv 20 Oct 2024.

Builds on

22 of 30 references.

References · 22

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 8,964
  4. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,067
  5. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 2,994
  6. 2023Consistency Modelscited by 1,778
  7. 2016WaveNet: A Generative Model for Raw Audiocited by 1,710
  8. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  9. 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,139
  10. 2020FastSpeech 2: Fast and High-Quality End-to-End Text to Speechcited by 710
  11. 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
  12. 2023VideoLCM: Video Latent Consistency Modelcited by 90
10 more
  1. 2024DITTO: Diffusion Inference-Time T-Optimization for Music Generationcited by 73
  2. 2017A Wavenet for Speech Denoisingcited by 47
  3. 2023CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Modelcited by 44
  4. 2020HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesiscited by 39
  5. 2020DeepSinger: Singing Voice Synthesis with Data Mined From the Webcited by 32
  6. 2023Amphion: An Open-Source Audio, Music and Speech Generation Toolkitcited by 25
  7. 2019Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformercited by 17
  8. 2024CM-TTS: Enhancing Real Time Text-to-Speech Synthesis Efficiency through Weighted Samplers and Consistency Modelscited by 13
  9. 2021RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responsescited by 5
  10. 2022Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GANcited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SmoothSinger: A Conditional Diffusion Model for Singing Voice Synthesis with Multi-Resolution Architecture
  2. 2025DiTSinger: Scaling Singing Voice Synthesis with Diffusion Transformer and Implicit Alignment
  3. 2024CoMoSVC: Consistency Model-based Singing Voice Conversion
  4. 2023HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Models
  5. 2026VocalRender: Score-Native Singing Voice Synthesis for Real-World Composition
  6. 2025TechSinger: Technique Controllable Multilingual Singing Voice Synthesis via Flow Matching
  7. 2025Generative Multi-modal Feedback for Singing Voice Synthesis Evaluation
  8. 2024CONTUNER: Singing Voice Beautifying with Pitch and Expressiveness Condition