research
∙
10/17/2017
Embedding-Based Speaker Adaptive Training of Deep Neural Networks
An embedding-based speaker adaptive training (SAT) approach is proposed ...
share
research
∙
02/27/2017
McGan: Mean and Covariance Feature Matching GAN
We introduce new families of Integral Probability Metrics (IPM) for trai...
research
∙
12/02/2016
Self-critical Sequence Training for Image Captioning
Recently it has been shown that policy-gradient methods for reinforcemen...
research
∙
11/28/2016
Dense Prediction on Sequences with Time-Dilated Convolutions for Speech Recognition
In computer vision pixelwise dense prediction is the task of predicting ...
research
∙
04/06/2016
Advances in Very Deep Convolutional Neural Networks for LVCSR
Very deep CNNs with small 3x3 kernels have recently been shown to achiev...
research
∙
06/11/2015
Random Maxout Features
In this paper, we propose and study random maxout features, which are co...
research
∙
01/22/2015