• Publications
  • Influence
Speech recognition with deep recurrent neural networks
tl;dr
This paper investigates deep recurrent neural networks, which combine the multiple levels of representation that have proved so effective in deep networks with the flexible use of long range context that empowers RNNs. Expand
  • 5,163
  • 304
  • Open Access
Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
tl;dr
DNNs for acoustic modeling in speech recognition can outperform Gaussian mixture models on speech recognition benchmarks. Expand
  • 5,883
  • 235
  • Open Access
Deep Neural Networks for Acoustic Modeling in Speech Recognition
tl;dr
Deep neural networks with many hidden layers, that are trained using new methods have been shown to outperform Gaussian mixture models on a variety of speech rec ognition benchmarks, sometimes by a large margin. Expand
  • 1,928
  • 140
  • Open Access
Acoustic Modeling Using Deep Belief Networks
tl;dr
We show that better phone recognition on TIMIT dataset can be achieved by replacing Gaussian mixture models by deep neural networks that contain many layers of features and a very large number of parameters. Expand
  • 1,475
  • 103
  • Open Access
Hybrid speech recognition with Deep Bidirectional LSTM
tl;dr
Deep Bidirectional LSTM (DBLSTM) recurrent neural networks have recently been shown to give state-of-the-art performance on TIMIT speech database. Expand
  • 973
  • 100
  • Open Access
Convolutional Neural Networks for Speech Recognition
tl;dr
We show that convolutional neural networks can reduce the error rate by 6%-10% compared with DNNs on the TIMIT phone recognition and the voice search large vocabulary speech recognition tasks. Expand
  • 1,070
  • 57
  • Open Access
Deep convolutional neural networks for LVCSR
tl;dr
Convolutional Neural Networks (CNNs) are an alternative type of neural network that can be used to reduce spectral variations and model spectral correlations which exist in signals. Expand
  • 789
  • 41
  • Open Access
Applying Convolutional Neural Networks concepts to hybrid NN-HMM model for speech recognition
tl;dr
We propose to use local filtering and max-pooling in frequency domain to normalize speaker variance to achieve higher multi-speaker speech recognition performance. Expand
  • 670
  • 36
  • Open Access
RobustFill: Neural Program Learning under Noisy I/O
tl;dr
The problem of automatically generating a computer program from some specification has been studied since the early days of AI. Expand
  • 177
  • 26
  • Open Access
Deep Belief Networks for phone recognition
tl;dr
We propose using Deep Belief Networks to model the spectral variabilities in speech. Expand
  • 355
  • 20
  • Open Access