mlsanityData to 7 Oct 2026

WaveFlow: A Compact Flow-based Model for Raw Audio

arXiv 1912.01219 ↗First posted 3 Dec 2019cs.SD cs.CL cs.LGcited by 51

Not on the map. Why?

Abstract (arXiv)

In this work, we propose WaveFlow, a small-footprint generative flow for raw audio, which is directly trained with maximum likelihood. It handles the long-range structure of 1-D waveform with a dilated 2-D convolutional architecture, while modeling the local variations using expressive autoregressive functions. WaveFlow provides a unified view of likelihood-based models for 1-D data, including WaveNet and WaveGlow as special cases. It generates high-fidelity speech as WaveNet, while synthesizing several orders of magnitude faster as it only requires a few sequential steps to generate very long waveforms with hundreds of thousands of time-steps. Furthermore, it can significantly reduce the likelihood gap that has existed between autoregressive models and flow-based models for efficient synthesis. Finally, our small-footprint WaveFlow has only 5.91M parameters, which is 15× smaller than WaveGlow. It can generate 22.05 kHz high-fidelity audio 42.6× faster than real-time (at a rate of 939.3 kHz) on a V100 GPU without engineered inference kernels.

Key facts. Cited by 51 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 19; 2022: 12; 2023: 7; 2024: 8; 2025: 3; 2026: 1.

51 papers.

Sort:

By area:

  1. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,339
  2. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 245
  3. 2021Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theorycited by 216
  4. 2021A Survey on Neural Speech Synthesiscited by 182
  5. 2022It's Raw! Audio Generation with State-Space Modelscited by 171
  6. 2021On Fast Sampling of Diffusion Probabilistic Modelscited by 170
  7. 2021D2C: Diffusion-Denoising Models for Few-shot Conditional Generationcited by 96
  8. 2023AUDIT: Audio Editing by Following Instructions with Latent Diffusion Modelscited by 81
  9. 2021PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Priorcited by 78
  10. 2021WaveFake: A Data Set to Facilitate Audio Deepfake Detectioncited by 78
  11. 2021NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsamplingcited by 50
  12. 2022SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shapingcited by 37
38 more
  1. 2024Autoregressive Diffusion Transformer for Text-to-Speech Synthesiscited by 34
  2. 2023AI-Generated Content (AIGC) for Various Data Modalities: A Surveycited by 25
  3. 2023Enabling AI-Generated Content (AIGC) Services in Wireless Edge Networkscited by 21
  4. 2022WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iterationcited by 20
  5. 2021Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamicscited by 19
  6. 2021Integrated Speech and Gesture Synthesiscited by 16
  7. 2021Catch-A-Waveform: Learning to Generate Audio from a Single Short Examplecited by 15
  8. 2024From Efficient Multimodal Models to World Models: A Surveycited by 13
  9. 2021Energy Consumption of Deep Generative Audio Modelscited by 12
  10. 2024FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocodercited by 11
  11. 2021Restoring degraded speech via a modified diffusion modelcited by 10
  12. 2021PassFlow: Guessing Passwords with Generative Flowscited by 10
  13. 2022RF-Next: Efficient Receptive Field Search for Convolutional Neural Networkscited by 10
  14. 2022Hierarchical Diffusion Models for Singing Voice Neural Vocodercited by 10
  15. 2022Audio representations for deep learning in sound synthesis: A reviewcited by 9
  16. 2024Universal Functional Regression with Neural Operator Flowscited by 9
  17. 2023A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inferencecited by 7
  18. 2025WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matchingcited by 7
  19. 2021Review of end-to-end speech synthesis technology based on deep learningcited by 6
  20. 2023BigVSAN: Enhancing GAN-based Neural Vocoders with Slicing Adversarial Networkcited by 6
  21. 2024Speaking in Wavelet Domain: A Simple and Efficient Approach to Speed up Speech Diffusion Modelcited by 6
  22. 2022Robust One-Shot Singing Voice Conversioncited by 5
  23. 2021Distilling the Knowledge from Conditional Normalizing Flowscited by 4
  24. 2023Deep Generative Modeling-based Data Augmentation with Demonstration using the BFBT Benchmark Void Fraction Datasetscited by 4
  25. 2024PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Modelcited by 3
  26. 2021On the Interplay Between Sparsity, Naturalness, Intelligibility, and Prosody in Speech Synthesiscited by 2
  27. 2022Generative Modeling for Low Dimensional Speech Attributes with Neural Spline Flowscited by 2
  28. 2022Controllable Accented Text-to-Speech Synthesiscited by 2
  29. 2023CleanUNet 2: A Hybrid Speech Denoising Model on Waveform and Spectrogramcited by 2
  30. 2021Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GANcited by 1
  31. 2025SupertonicTTS: Towards Highly Efficient and Streamlined Text-to-Speech Systemcited by 1
  32. 2021AudioVisual Speech Synthesis: A brief literature reviewcited by 0
  33. 2021FlowVocoder: A small Footprint Neural Vocoder based Normalizing flow for Speech Synthesiscited by 0
  34. 2022WOLONet: Wave Outlooker for Efficient and High Fidelity Speech Synthesiscited by 0
  35. 2022Multisymplectic Formulation of Deep Learning Using Mean--Field Type Control and Nonlinear Stability of Training Algorithmcited by 0
  36. 2024Music Style Transfer With Diffusion Modelcited by 0
  37. 2024Enhancing Kurdish Text-to-Speech with Native Corpus Training: A High-Quality WaveGlow Vocoder Approachcited by 0
  38. 2025BridgeVoC: Revitalizing Neural Vocoder from a Restoration Perspectivecited by 0

50 most cited of 51 All 51 (JSON)