• Publications
  • Influence
Rectifier Nonlinearities Improve Neural Network Acoustic Models
Deep neural network acoustic models produce substantial gains in large vocabulary continuous speech recognition systems. Emerging work with rectified linear (ReL) hidden units demonstrates additionalExpand
  • 2,691
  • 402
  • PDF
Maximum Entropy Inverse Reinforcement Learning
Recent research has shown the benefit of framing problems of imitation learning as solutions to Markov Decision Problems. This approach reduces learning to the problem of recovering a utilityExpand
  • 1,369
  • 262
  • PDF
Learning Word Vectors for Sentiment Analysis
Unsupervised vector-based approaches to semantics can model rich lexical meanings, but they largely fail to capture sentiment information that is central to many word meanings and important for aExpand
  • 1,956
  • 229
  • PDF
Recurrent Neural Networks for Noise Reduction in Robust ASR
Recent work on deep neural networks as acoustic models for automatic speech recognition (ASR) have demonstrated substantial performance improvements. We introduce a model which uses a deep recurrentExpand
  • 278
  • 20
  • PDF
Lexicon-Free Conversational Speech Recognition with Neural Networks
We present an approach to speech recognition that uses only a neural network to map acoustic input to characters, a character-level language model, and a beam search decoding procedure. This approachExpand
  • 111
  • 13
  • PDF
First-Pass Large Vocabulary Continuous Speech Recognition using Bi-Directional Recurrent DNNs
We present a method to perform first-pass large vocabulary co ntinuous speech recognition using only a neural network and language model. Deep neural network acoustic models are now commonplace inExpand
  • 94
  • 11
  • PDF
Navigate like a cabbie: probabilistic reasoning from observed context-aware behavior
We present PROCAB, an efficient method for Probabilistically Reasoning from Observed Context-Aware Behavior. It models the context-dependent utilities and underlying reasons that people takeExpand
  • 264
  • 10
  • PDF
Building DNN acoustic models for large vocabulary speech recognition
Deep neural networks (DNNs) are now a central component of nearly all state-of-the-art speech recognition systems. Building neural network acoustic models requires several design decisions includingExpand
  • 52
  • 3
  • PDF
A Probabilistic Model for Semantic Word Vectors
Vector representations of words capture relationships in words’ functions and meanings. Many existing techniques for inducing such representations from data use a pipeline of hand-coded processingExpand
  • 42
  • 2
  • PDF
Spectral Chinese Restaurant Processes: Nonparametric Clustering Based on Similarities
We introduce a new nonparametric clustering model which combines the recently proposed distance-dependent Chinese restaurant process (dd-CRP) and non-linear, spectral methods for dimensionalityExpand
  • 36
  • 2
  • PDF