Samy Bengio

End-to-end text-dependent speaker verification

2016

In this paper we present a data-driven, integrated approach to speaker verification, which maps a test utterance and a few reference utterances directly to a single score for verification and jointly optimizes the system's components …

Show and tell: A neural image caption generator

2015

Automatically describing the content of an image is a fundamental problem in artificial intelligence that connects computer vision and natural language processing. In this paper, we present a generative model based on a deep recurrent …

Order Matters: Sequence to sequence for sets

2015 · arXiv (Cornell University)

Sequences have become first class citizens in supervised learning thanks to the resurgence of recurrent neural networks. Many complex tasks that require mapping from or to a sequence of observations can now be formulated with …

Generating Sentences from a Continuous Space

2016

The standard recurrent neural network language model (rnnlm) generates sentences one word at a time and does not work from an explicit global sentence representation. In this work, we introduce and study an rnn-based variational …

Reward Augmented Maximum Likelihood for Neural Structured Prediction

2016 · arXiv (Cornell University)

A key problem in structured output prediction is direct optimization of the task reward function that matters for test evaluation. This paper presents a simple and computationally efficient approach to incorporate task reward into a …

Fast Decoding in Sequence Models using Discrete Latent Variables

2018 · arXiv (Cornell University)

Autoregressive sequence models based on deep neural networks, such as RNNs, Wavenet and the Transformer attain state-of-the-art results on many tasks. However, they are difficult to parallelize and are thus slow at processing long sequences. …

Content preserving text generation with attribute controls

2018 · arXiv (Cornell University)

In this work, we address the problem of modifying textual attributes of sentences. Given an input sentence and a set of attribute labels, we attempt to generate sentences that are compatible with the conditioning information. …

Cluster-GCN

2019

Graph convolutional network (GCN) has been successfully applied to many graph-based applications; however, training a large-scale GCN remains challenging. Current SGD-based algorithms suffer from either a high computational cost that exponentially grows with number of …

Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks

2015 · arXiv (Cornell University)

Recurrent Neural Networks can be trained to produce sequences of tokens given some input, as exemplified by recent results in machine translation and image captioning. The current approach to training them consists of maximizing the …

Tacotron: Towards End-to-End Speech Synthesis

2017

A text-to-speech synthesis system typically consists of multiple stages, such as a text analysis frontend, an acoustic model and an audio synthesis module.Building these components often requires extensive domain expertise and may contain brittle design …