• Publications
  • Influence
WaveNet: A Generative Model for Raw Audio
tl;dr
This paper introduces WaveNet, a deep neural network for generating raw audio waveforms. Expand
  • 2,757
  • 455
Open Access
Mastering the game of Go with deep neural networks and tree search
tl;dr
The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Expand
  • 7,275
  • 300
Open Access
A Convolutional Neural Network for Modelling Sentences
tl;dr
We describe a convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) that we adopt for the semantic modelling of sentences. Expand
  • 2,337
  • 201
Open Access
Pixel Recurrent Neural Networks
tl;dr
We present a deep neural network that sequentially predicts the pixels in an image along the two spatial dimensions. Expand
  • 1,218
  • 142
Open Access
Conditional Image Generation with PixelCNN Decoders
tl;dr
We combine the strengths of both models by introducing a gated variant of PixelCNN (Gated PixelCNN) that matches the log-likelihood of PixelRNN on both CIFAR and ImageNet. Expand
  • 1,039
  • 114
Open Access
Recurrent Continuous Translation Models
tl;dr
We introduce a class of probabilistic continuous translation models called Recurrent Continuous Translation Models that are purely based on continuous representations for words, phrases and sentences and do not rely on alignments or phrasal translation units. Expand
  • 994
  • 66
Open Access
Parallel WaveNet: Fast High-Fidelity Speech Synthesis
tl;dr
This paper introduces Probability Density Distillation, a new method for training a parallel feed-forward network from a trained WaveNet with no significant difference in quality. Expand
  • 369
  • 65
Open Access
Grid Long Short-Term Memory
tl;dr
This paper introduces Grid Long Short-Term Memory, a network of LSTM cells arranged in a multidimensional grid that can be applied to vectors, sequences or higher dimensional data. Expand
  • 266
  • 47
Open Access
Efficient Neural Audio Synthesis
tl;dr
We propose a single-layer recurrent neural network, the WaveRNN, with a dual softmax layer that matches the quality of the state-of-the-art WaveNet model. Expand
  • 237
  • 44
Open Access
Neural Machine Translation in Linear Time
tl;dr
The ByteNet is a one-dimensional convolutional neural network that is composed of two parts, one to encode the source sequence and the other to decode the target sequence. Expand
  • 341
  • 35
Open Access