Statements (27)
| Predicate | Object |
|---|---|
| gptkbp:instanceOf |
gptkb:convolutional_neural_network
|
| gptkbp:application |
text-to-speech
voice conversion |
| gptkbp:author |
gptkb:Aaron_Courville
gptkb:Yoshua_Bengio gptkb:Kundan_Kumar Alexandre de Brébisson Jose Sotelo Lucas Gestin Rithesh Kumar Thibault de Boissiere Wei Zhen Teoh |
| gptkbp:basedOn |
GAN architecture
|
| gptkbp:citation |
https://arxiv.org/abs/1910.06711
MelGAN: Generative Adversarial Networks for Conditional Waveform Synthesis |
| gptkbp:developedBy |
speech synthesis
|
| gptkbp:input |
mel-spectrogram
|
| gptkbp:introducedIn |
2019
|
| gptkbp:notableFor |
high-quality audio
real-time speech synthesis non-autoregressive generation |
| gptkbp:openSource |
yes
|
| gptkbp:output |
audio waveform
|
| gptkbp:publishedIn |
gptkb:arXiv
|
| gptkbp:bfsParent |
gptkb:WaveRNN
|
| gptkbp:bfsLayer |
7
|
| https://www.w3.org/2000/01/rdf-schema#label |
MelGAN
|