• Publications
  • Influence
Document-Level Neural Machine Translation with Hierarchical Attention Networks
TLDR
Neural Machine Translation (NMT) can be improved by including document-level contextual information in a structured and dynamic manner. Expand
  • 87
  • 38
  • PDF
Sparse modeling of posterior exemplars for keyword detection
TLDR
We propose a new keyword detection algorithm based on sparse representation of the posterior exemplars. Expand
  • 13
  • 1
  • PDF
Self-Attentive Residual Decoder for Neural Machine Translation
TLDR
Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. Expand
  • 9
  • 1
  • PDF
CNN Based Query by Example Spoken Term Detection
TLDR
In this work, we address the problem of query by example spoken term detection (QbE-STD) in zero-resource scenario. Expand
  • 5
  • 1
  • PDF
Subspace Detection of DNN Posterior Probabilities via Sparse Representation for Query by Example Spoken Term Detection
TLDR
We cast the query by example spoken term detection (QbE-STD) problem as subspace detection where query and background subspaces are modeled as union of low-dimensional subspace. Expand
  • 11
  • PDF
Sparse Subspace Modeling for Query by Example Spoken Term Detection
TLDR
We investigate three different QbE-STD systems based on sparse model recovery. Expand
  • 12
  • PDF
Phonetic subspace features for improved query by example spoken term detection
TLDR
We exploit Deep Neural Networks (DNNs) and the so inferred phone posteriors to better model the phonetic subspaces and improve the QbE-STD performance. Expand
  • 5
  • PDF
Subspace Regularized Dynamic Time Warping for Spoken Query Detection
TLDR
We exploit the query example as the dictionary for sparse recovery. Expand
  • 6
  • PDF
Multilingual Bottleneck Features for Query by Example Spoken Term Detection
TLDR
We present a study on QbE-STD performance using several monolingual as well as multilingual bottleneck features extracted from feed forward networks. Expand
  • 4
  • PDF
Neural Network Based End-to-End Query by Example Spoken Term Detection
TLDR
This article focuses on the problem of query by example spoken term detection (QbE-STD) in zero-resource scenario. Expand
  • 2
  • PDF