Search Results for author: Aäron van den Oord

Found 15 papers, 7 papers with code

Vector Quantized Models for Planning

no code implementations8 Jun 2021 Sherjil Ozair, Yazhe Li, Ali Razavi, Ioannis Antonoglou, Aäron van den Oord, Oriol Vinyals

Our key insight is to use discrete autoencoders to capture the multiple possible effects of an action in a stochastic environment.

Predicting Video with VQVAE

1 code implementation2 Mar 2021 Jacob Walker, Ali Razavi, Aäron van den Oord

In recent years, the task of video prediction-forecasting future video given past video frames-has attracted attention in the research community.

Video Generation Video Prediction

Low Bit-Rate Speech Coding with VQ-VAE and a WaveNet Decoder

no code implementations14 Oct 2019 Cristina Gârbacea, Aäron van den Oord, Yazhe Li, Felicia S. C. Lim, Alejandro Luebs, Oriol Vinyals, Thomas C. Walters

In order to efficiently transmit and store speech signals, speech codecs create a minimally redundant representation of the input signal which is then decoded at the receiver with the best possible perceptual quality.

Visual Imitation with a Minimal Adversary

no code implementations ICLR 2019 Scott Reed, Yusuf Aytar, Ziyu Wang, Tom Paine, Aäron van den Oord, Tobias Pfaff, Sergio Gomez, Alexander Novikov, David Budden, Oriol Vinyals

The proposed agent can solve a challenging robot manipulation task of block stacking from only video demonstrations and sparse reward, in which the non-imitating agents fail to learn completely.

Imitation Learning Robot Manipulation

Unsupervised speech representation learning using WaveNet autoencoders

5 code implementations25 Jan 2019 Jan Chorowski, Ron J. Weiss, Samy Bengio, Aäron van den Oord

We consider the task of unsupervised extraction of meaningful latent representations of speech by applying autoencoding neural networks to speech waveforms.

Acoustic Unit Discovery Dimensionality Reduction +1

Preventing Posterior Collapse with delta-VAEs

no code implementations ICLR 2019 Ali Razavi, Aäron van den Oord, Ben Poole, Oriol Vinyals

Due to the phenomenon of "posterior collapse," current latent variable generative models pose a challenging design choice that either weakens the capacity of the decoder or requires augmenting the objective so it does not only maximize the likelihood of the data.

Ranked #6 on Image Generation on ImageNet 32x32 (bpd metric)

Image Generation Representation Learning

The challenge of realistic music generation: modelling raw audio at scale

no code implementations NeurIPS 2018 Sander Dieleman, Aäron van den Oord, Karen Simonyan

It has been shown that autoregressive models excel at generating raw audio waveforms of speech, but when applied to music, we find them biased towards capturing local signal structure at the expense of modelling long-range correlations.

Music Generation

Parallel Multiscale Autoregressive Density Estimation

no code implementations ICML 2017 Scott Reed, Aäron van den Oord, Nal Kalchbrenner, Sergio Gómez Colmenarejo, Ziyu Wang, Dan Belov, Nando de Freitas

Our new PixelCNN model achieves competitive density estimation and orders of magnitude speedup - O(log N) sampling instead of O(N) - enabling the practical generation of 512x512 images.

Conditional Image Generation Density Estimation +2

A note on the evaluation of generative models

1 code implementation5 Nov 2015 Lucas Theis, Aäron van den Oord, Matthias Bethge

In particular, we show that three of the currently most commonly used criteria---average log-likelihood, Parzen window estimates, and visual fidelity of samples---are largely independent of each other when the data is high-dimensional.

Denoising Texture Synthesis

Cannot find the paper you are looking for? You can Submit a new open access paper.