Adversarial Audio Synthesis

Chris Donahue, Julian McAuley, Miller Puckette
2/12/2018
cs.SDcs.LG

Official code: chrisdonahue/wavegan (1,382 stars, MIT, last commit 2022-11-27).

Abstract

Audio signals are sampled at high temporal resolutions, and learning to synthesize audio requires capturing structure across a range of timescales. Generative adversarial networks (GANs) have seen wide success at generating images that are both locally and globally coherent, but they have seen little application to audio generation. In this paper we introduce WaveGAN, a first attempt at applying GANs to unsupervised synthesis of raw-waveform audio. WaveGAN is capable of synthesizing one second slices of audio waveforms with global coherence, suitable for sound effect generation. Our experiments demonstrate that, without labels, WaveGAN learns to produce intelligible words when trained on a small-vocabulary speech dataset, and can also synthesize audio from other domains such as drums, bird vocalizations, and piano. We compare WaveGAN to a method which applies GANs designed for image generation on image-like audio feature representations, finding both approaches to be promising.

View on arXivView PDF

Code Implementations(1)

chrisdonahue/waveganOfficial100%
MIT

WaveGAN: Learn to synthesize raw audio with generative adversarial networks

1,382280CSS, HTMLFeb 9, 20183 years agoMIT

Similar Papers

HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis

86% match1 repo2.4k2020

High Fidelity Speech Synthesis with Adversarial Networks

85% match1 repo1302019

Disentanglement in a GAN for Unconditional Speech Synthesis

85% match1 repo622023

Gotta Hear Them All: Towards Sound Source Aware Audio Generation

83% match1 repo702024

SampleRNN: An Unconditional End-to-End Neural Audio Generation Model

83% match1 repo5432016

RAVE: A variational autoencoder for fast and high-quality neural audio synthesis

82% match1 repo1.8k2021

Cite this paper

@article{donahue2018adversarial,
  title  = {Adversarial Audio Synthesis},
  author = {Chris Donahue and Julian McAuley and Miller Puckette},
  year   = {2018},
  eprint = {1802.04208},
  archivePrefix = {arXiv},
  url    = {https://arxiv.org/abs/1802.04208}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/1802.04208.svg)](https://codeofpaper.com/paper/1802.04208)

Discussion