WaveNet: A Generative Model for Raw Audio
- Aäron van den Oord, S. Dieleman, K. Kavukcuoglu
- Computer ScienceSpeech Synthesis Workshop
- 12 September 2016
WaveNet, a deep neural network for generating raw audio waveforms, is introduced; it is shown that it can be efficiently trained on data with tens of thousands of samples per second of audio, and can be employed as a discriminative model, returning promising results for phoneme recognition.
Mastering the game of Go with deep neural networks and tree search
- David Silver, Aja Huang, D. Hassabis
- Computer ScienceNature
- 28 January 2016
Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go.
A Convolutional Neural Network for Modelling Sentences
- Nal Kalchbrenner, Edward Grefenstette, P. Blunsom
- Computer ScienceAnnual Meeting of the Association for…
- 8 April 2014
A convolutional architecture dubbed the Dynamic Convolutional Neural Network (DCNN) is described that is adopted for the semantic modelling of sentences and induces a feature graph over the sentence that is capable of explicitly capturing short and long-range relations.
Pixel Recurrent Neural Networks
- Aäron van den Oord, Nal Kalchbrenner, K. Kavukcuoglu
- Computer ScienceInternational Conference on Machine Learning
- 25 January 2016
A deep neural network is presented that sequentially predicts the pixels in an image along the two spatial dimensions and encodes the complete set of dependencies in the image to achieve log-likelihood scores on natural images that are considerably better than the previous state of the art.
Conditional Image Generation with PixelCNN Decoders
- Aäron van den Oord, Nal Kalchbrenner, Lasse Espeholt, K. Kavukcuoglu, Oriol Vinyals, A. Graves
- Computer ScienceNIPS
- 16 June 2016
The gated convolutional layers in the proposed model improve the log-likelihood of PixelCNN to match the state-of-the-art performance of PixelRNN on ImageNet, with greatly reduced computational cost.
Efficient Neural Audio Synthesis
- Nal Kalchbrenner, Erich Elsen, K. Kavukcuoglu
- Computer ScienceInternational Conference on Machine Learning
- 23 February 2018
A single-layer recurrent neural network with a dual softmax layer that matches the quality of the state-of-the-art WaveNet model, the WaveRNN, and a new generation scheme based on subscaling that folds a long sequence into a batch of shorter sequences and allows one to generate multiple samples at once.
Recurrent Continuous Translation Models
- Nal Kalchbrenner, P. Blunsom
- Computer ScienceConference on Empirical Methods in Natural…
- 1 October 2013
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…
Parallel WaveNet: Fast High-Fidelity Speech Synthesis
- Aäron van den Oord, Yazhe Li, D. Hassabis
- Computer ScienceInternational Conference on Machine Learning
- 28 November 2017
The recently-developed WaveNet architecture is the current state of the art in realistic speech synthesis, consistently rated as more natural sounding for many different languages than any previous…
Toward Causal Representation Learning
- B. Scholkopf, Francesco Locatello, Yoshua Bengio
- Computer Science, PhilosophyProceedings of the IEEE
- 22 February 2021
Fundamental concepts of causal inference are reviewed and related to crucial open problems of machine learning, including transfer and generalization, thereby assaying how causality can contribute to modern machine learning research.
Grid Long Short-Term Memory
- Nal Kalchbrenner, Ivo Danihelka, A. Graves
- Computer ScienceInternational Conference on Learning…
- 6 July 2015
The Grid LSTM is used to define a novel two-dimensional translation model, the Reencoder, and it is shown that it outperforms a phrase-based reference system on a Chinese-to-English translation task.
...
...