WaveGAN¶

Description¶

WaveGAN is a machine learning algorithm which learns to synthesize raw waveform audio by observing many examples of real audio. WaveGAN is comparable to the popular DCGAN approach (Radford et al. 2016) for learning to generate images.

Environment Modules¶

Run module spider wavegan to find out what environment modules are available for this application.

Environment Variables¶

HPC_WAVEGAN_DIR - installation directory
HPC_WAVEGAN_BIN - executable directory

Additional Usage Information¶

You must specify the full path to the script when running it. The HPC_WAVEGAN_DIR convenience environment variable can be used to accomplish this:

python ${HPC_WAVEGAN_DIR}/train_wavegan.py --help

Citation¶

If you publish research that uses WaveGAN you have to cite it as follows:

@inproceedings{donahue2019wavegan,
    title={Adversarial Audio Synthesis},
    author={Donahue, Chris and McAuley, Julian and Puckette, Miller},
    booktitle={ICLR},
    year={2019}
}

Categories¶

machine_learning, audio, GAN