Generative Audio Models

Edit

Audio • 17 methods

Methods

Add a Method

Method	Year	Papers
WaveNet WaveNet: A Generative Model for Raw Audio	2016	157
WaveGAN Adversarial Audio Synthesis	2018	29
HiFi-GAN HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis	2020	28
WaveRNN Efficient Neural Audio Synthesis	2018	26
COLA Contrastive Learning of General-Purpose Audio Representations	2020	25
WaveGlow WaveGlow: A Flow-based Generative Network for Speech Synthesis	2018	20
MelGAN MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis	2019	14
DDSP DDSP: Differentiable Digital Signal Processing	2020	10
Jukebox Jukebox: A Generative Model for Music	2020	10
WaveGrad WaveGrad: Estimating Gradients for Waveform Generation	2020	7
AccoMontage AccoMontage: Accompaniment Arrangement via Phrase Selection and Style Transfer	2021	2
CTAL CTAL: Pre-training Cross-modal Transformer for Audio-and-Language Representations	2021	2
SpecGAN Adversarial Audio Synthesis	2018	1
WaveVAE Non-Autoregressive Neural Text-to-Speech	2019	1
VocGAN VocGAN: A High-Fidelity Real-time Vocoder with a Hierarchically-nested Adversarial Network	2020	1
Multi-band MelGAN Multi-band MelGAN: Faster Waveform Generation for High-Quality Text-to-Speech	2020	1