MelGAN: Generative Adversarial Networks for Conditional Waveform SynthesisEI

    Kundan Kumar
    Kundan Kumar
    Rithesh Kumar
    Rithesh Kumar
    Thibault de Boissiere
    Thibault de Boissiere
    Lucas Gestin
    Lucas Gestin
    Wei Zhen Teoh
    Wei Zhen Teoh
    Jose Sotelo
    Jose Sotelo
    Alexandre de Brébisson
    Alexandre de Brébisson
    Click here to see all papers in nips2019
    Cited by: 0|Bibtex|66|

    NeurIPS, pp. 14881-14892, 2019.

    Keywords:
    generative adversarial network (gan)

    Abstract:

    Previous works (Donahue et al., 2018a; Engel et al., 2019a) have found that generating coherent raw audio waveforms with GANs is challenging. In this paper, we show that it is possible to train GANs reliably to generate high quality coherent waveforms by introducing a set of architectural changes and simple training techniques. Subjective...More
    Your rating :
    0

     

    Tags
    Comments