WaveNet

E39544

autoregressive model deep generative model neural network architecture text-to-speech model

WaveNet is a deep generative neural network architecture for raw audio that produces highly natural-sounding speech and other audio signals.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (3)

Label	Occurrences
WaveNet canonical	12
WaveNet: A Generative Model for Raw Audio	3
WaveNet voices	1

Statements (51)

Predicate	Object
instanceOf	autoregressive model ⓘ deep generative model ⓘ neural network architecture ⓘ text-to-speech model ⓘ
application	music generation ⓘ neural vocoder for parametric TTS ⓘ voice conversion ⓘ
arxivId	1609.03499 ⓘ
basedOn	causal convolutional neural networks ⓘ
designedFor	audio signal modeling ⓘ raw audio generation ⓘ speech synthesis ⓘ
developedBy	DeepMind ⓘ DeepMind ⓘ surface form: Google DeepMind
hasProperty	high computational cost at inference ⓘ highly natural-sounding speech output ⓘ parallelization across time is limited by autoregressive structure ⓘ
improvedUpon	concatenative text-to-speech systems ⓘ parametric HMM-based TTS systems ⓘ
inputType	discretized audio waveform samples ⓘ
inspired	PixelCNN ⓘ
introducedBy	Aaron van den Oord ⓘ Alex Graves ⓘ Heiga Zen ⓘ Karen Simonyan ⓘ Nal Kalchbrenner ⓘ Oriol Vinyals ⓘ Sander Dieleman ⓘ
introducedIn	2016 ⓘ
introducedInPaper	WaveNet self-linksurface differs ⓘ surface form: WaveNet: A Generative Model for Raw Audio
language	Python ⓘ
ledTo	Parallel WaveNet ⓘ WaveGlow ⓘ WaveRNN ⓘ neural vocoder architectures ⓘ
outputType	probability distribution over next audio sample ⓘ
publishedAt	arXiv ⓘ
relatedTo	PixelRNN ⓘ autoregressive image models ⓘ
supports	general raw waveform modeling ⓘ music audio generation ⓘ speaker-conditioned speech synthesis ⓘ text-conditioned speech synthesis ⓘ
trainingObjective	cross-entropy loss over quantized samples ⓘ maximum likelihood estimation ⓘ
usedIn	Google Assistant ⓘ surface form: Google Assistant text-to-speech Google Cloud Text-to-Speech ⓘ
uses	autoregressive sample-by-sample prediction ⓘ conditional generative modeling ⓘ dilated causal convolutions ⓘ softmax output over quantized audio samples ⓘ

Referenced by (16)

Full triples — surface form annotated when it differs from this entity's canonical label.

DeepMind → developed → WaveNet ⓘ

WaveNet → introducedInPaper → WaveNet self-linksurface differs ⓘ

this entity surface form: WaveNet: A Generative Model for Raw Audio

Heiga Zen → notableWork → WaveNet ⓘ

this entity surface form: WaveNet: A Generative Model for Raw Audio

Nal Kalchbrenner → notableWork → WaveNet ⓘ

Nal Kalchbrenner → coDeveloperOf → WaveNet ⓘ

WaveRNN → comparedTo → WaveNet ⓘ

WaveRNN → improvesOn → WaveNet ⓘ

WaveRNN → moreEfficientThan → WaveNet ⓘ

WaveGlow → basedOn → WaveNet ⓘ

WaveGlow → comparedWith → WaveNet ⓘ

Karen Simonyan → knownFor → WaveNet ⓘ

Google Cloud Text-to-Speech → supports → WaveNet ⓘ

this entity surface form: WaveNet voices

Parallel WaveNet → basedOn → WaveNet ⓘ

Aaron van den Oord → knownFor → WaveNet ⓘ

Aaron van den Oord → developed → WaveNet ⓘ

Aaron van den Oord → notableWork → WaveNet ⓘ

this entity surface form: WaveNet: A Generative Model for Raw Audio