|
gptkbp:instanceOf
|
gptkb:model
|
|
gptkbp:architecture
|
gptkb:convolutional_neural_network
|
|
gptkbp:arXivID
|
1609.03499
|
|
gptkbp:author
|
gptkb:Koray_Kavukcuoglu
gptkb:Aaron_van_den_Oord
gptkb:Andrew_Senior
gptkb:Heiga_Zen
gptkb:Nal_Kalchbrenner
gptkb:Sander_Dieleman
gptkb:Alex_Graves
gptkb:Oriol_Vinyals
gptkb:Karen_Simonyan
|
|
gptkbp:category
|
gptkb:artificial_intelligence
gptkb:model
gptkb:public_speaker
gptkb:convolutional_neural_network
audio processing
|
|
gptkbp:citation
|
gptkb:WaveNet:_A_Generative_Model_for_Raw_Audio
2016
|
|
gptkbp:developedBy
|
gptkb:DeepMind
|
|
gptkbp:hasComponent
|
dilated convolutions
residual connections
skip connections
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
WaveNet
|
|
gptkbp:influenced
|
gptkb:Parallel_WaveNet
gptkb:Tacotron
gptkb:WaveRNN
|
|
gptkbp:input
|
raw audio waveforms
|
|
gptkbp:introducedIn
|
2016
|
|
gptkbp:language
|
gptkb:Python
|
|
gptkbp:notableFor
|
generating realistic human speech
improving naturalness of synthesized speech
inspiring neural vocoders
|
|
gptkbp:openSource
|
gptkb:NVIDIA_WaveGlow
gptkb:ibab/tensorflow-wavenet
gptkb:r9y9/wavenet_vocoder
|
|
gptkbp:output
|
audio waveforms
|
|
gptkbp:publishedIn
|
gptkb:arXiv
|
|
gptkbp:relatedTo
|
gptkb:machine_learning
deep learning
generative models
text-to-speech
audio synthesis
autoregressive models
|
|
gptkbp:usedBy
|
gptkb:Google_Assistant
gptkb:Google_Cloud_Text-to-Speech
|
|
gptkbp:usedFor
|
speech synthesis
audio generation
|
|
gptkbp:bfsParent
|
gptkb:DeepMind
gptkb:Cloud_Text-to-Speech
|
|
gptkbp:bfsLayer
|
5
|