Stripped Down Vocoder from SpecVQGAN

Original project:

• [Project Page] • [ArXiv] •

Purpose of this is educational. A simple demo showing how a mel spectrogram can be transformed via a neural vocoder into audio.

Citation

@InProceedings{SpecVQGAN_Iashin_2021,
  title={Taming Visually Guided Sound Generation},
  author={Iashin, Vladimir and Rahtu, Esa},
  booktitle={British Machine Vision Conference (BMVC)},
  year={2021}
}