gptkbp:instanceOf
|
gptkb:convolutional_neural_network
|
gptkbp:advantage
|
low computational cost
lower quality than some autoregressive models
real-time synthesis
|
gptkbp:architecture
|
recurrent neural network
|
gptkbp:author
|
gptkb:Koray_Kavukcuoglu
gptkb:Aaron_van_den_Oord
gptkb:Nal_Kalchbrenner
gptkb:Sander_Dieleman
gptkb:Karen_Simonyan
gptkb:Edward_Lockhart
gptkb:Erich_Elsen
gptkb:Florian_Stimberg
gptkb:Norman_Casagrande
gptkb:Seb_Noury
|
gptkbp:canBe
|
gptkb:microprocessor
gptkb:graphics_card
|
gptkbp:citation
|
2018
|
gptkbp:contrastsWith
|
gptkb:WaveNet
|
gptkbp:designedFor
|
efficient audio generation
|
gptkbp:developedBy
|
gptkb:DeepMind
|
gptkbp:github
|
https://github.com/fatchord/WaveRNN
|
https://www.w3.org/2000/01/rdf-schema#label
|
WaveRNN
|
gptkbp:input
|
acoustic features
|
gptkbp:introducedIn
|
2018
|
gptkbp:notablePublication
|
gptkb:Efficient_Neural_Audio_Synthesis
|
gptkbp:openSource
|
yes
|
gptkbp:output
|
audio waveform
|
gptkbp:publishedIn
|
gptkb:arXiv
|
gptkbp:relatedTo
|
gptkb:Parallel_WaveNet
gptkb:Tacotron
gptkb:HiFi-GAN
gptkb:MelGAN
|
gptkbp:usedFor
|
speech synthesis
text-to-speech
|
gptkbp:bfsParent
|
gptkb:WaveNet
|
gptkbp:bfsLayer
|
6
|