# WaveFlow: A Compact Flow-based Model for Raw Audio

arXiv: https://arxiv.org/abs/1912.01219 · HTML: https://mlsanity.com/paper/1912.01219/

## Key facts

- Cited by 51 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Dec 2019.

## Built on by (most cited first, 30 of 51)

- [DiffWave: A Versatile Diffusion Model for Audio Synthesis](https://mlsanity.com/paper/2009.09761/) (2020)
- [BigVGAN: A Universal Neural Vocoder with Large-Scale Training](https://mlsanity.com/paper/2206.04658/) (2022)
- [Likelihood Training of Schr"odinger Bridge using Forward-Backward SDEs Theory](https://mlsanity.com/paper/2110.11291/) (2021)
- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [It's Raw! Audio Generation with State-Space Models](https://mlsanity.com/paper/2202.09729/) (2022)
- [On Fast Sampling of Diffusion Probabilistic Models](https://mlsanity.com/paper/2106.00132/) (2021)
- [D2C: Diffusion-Denoising Models for Few-shot Conditional Generation](https://mlsanity.com/paper/2106.06819/) (2021)
- [AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models](https://mlsanity.com/paper/2304.00830/) (2023)
- [PriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior](https://mlsanity.com/paper/2106.06406/) (2021)
- [WaveFake: A Data Set to Facilitate Audio Deepfake Detection](https://mlsanity.com/paper/2111.02813/) (2021)
- [NU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling](https://mlsanity.com/paper/2104.02321/) (2021)
- [SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping](https://mlsanity.com/paper/2203.16749/) (2022)
- [Autoregressive Diffusion Transformer for Text-to-Speech Synthesis](https://mlsanity.com/paper/2406.05551/) (2024)
- [AI-Generated Content (AIGC) for Various Data Modalities: A Survey](https://mlsanity.com/paper/2308.14177/) (2023)
- [Enabling AI-Generated Content (AIGC) Services in Wireless Edge Networks](https://mlsanity.com/paper/2301.03220/) (2023)
- [WaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration](https://mlsanity.com/paper/2210.01029/) (2022)
- [Parallel and Flexible Sampling from Autoregressive Models via Langevin Dynamics](https://mlsanity.com/paper/2105.08164/) (2021)
- [Integrated Speech and Gesture Synthesis](https://mlsanity.com/paper/2108.11436/) (2021)
- [Catch-A-Waveform: Learning to Generate Audio from a Single Short Example](https://mlsanity.com/paper/2106.06426/) (2021)
- [From Efficient Multimodal Models to World Models: A Survey](https://mlsanity.com/paper/2407.00118/) (2024)
- [Energy Consumption of Deep Generative Audio Models](https://mlsanity.com/paper/2107.02621/) (2021)
- [FreGrad: Lightweight and Fast Frequency-aware Diffusion Vocoder](https://mlsanity.com/paper/2401.10032/) (2024)
- [Restoring degraded speech via a modified diffusion model](https://mlsanity.com/paper/2104.11347/) (2021)
- [PassFlow: Guessing Passwords with Generative Flows](https://mlsanity.com/paper/2105.06165/) (2021)
- [RF-Next: Efficient Receptive Field Search for Convolutional Neural Networks](https://mlsanity.com/paper/2206.06637/) (2022)
- [Hierarchical Diffusion Models for Singing Voice Neural Vocoder](https://mlsanity.com/paper/2210.07508/) (2022)
- [Audio representations for deep learning in sound synthesis: A review](https://mlsanity.com/paper/2201.02490/) (2022)
- [Universal Functional Regression with Neural Operator Flows](https://mlsanity.com/paper/2404.02986/) (2024)
- [A Tale of Two Latent Flows: Learning Latent Space Normalizing Flow with Short-run Langevin Flow for Approximate Inference](https://mlsanity.com/paper/2301.09300/) (2023)
- [WaveFM: A High-Fidelity and Efficient Vocoder Based on Flow Matching](https://mlsanity.com/paper/2503.16689/) (2025)

## 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.