• Publications
  • Influence
Class-Based n-gram Models of Natural Language
We address the problem of predicting a word from previous words in a sample of text using n-gram models based on classes of words. Expand
  • 3,083
  • 235
  • PDF
Maximum mutual information estimation of hidden Markov model parameters for speech recognition
A method for estimating the parameters of hidden Markov models of speech is described. Expand
  • 891
  • 71
  • PDF
A tree-based statistical language model for natural language speech recognition
The problem of predicting the next word a speaker will say, given the words already spoken; is discussed. Expand
  • 284
  • 14
Estimating hidden Markov model parameters so as to maximize speech recognition accuracy
The problem of estimating the parameter values of hidden Markov word models for speech recognition is addressed. Expand
  • 77
  • 5
A new algorithm for the estimation of hidden Markov model parameters
We propose an alternative estimation procedure called corrective training which is aimed at minimizing the number of recognition errors. Expand
  • 128
  • 4
Decision trees for phonological rules in continuous speech
The authors present an automatic method for modeling phonological variation using decision trees. Expand
  • 153
  • 3
Robust methods for using context-dependent features and models in a continuous speech recognizer
In this paper we describe the method we use to derive acoustic features that reflect some of the dynamics of frame-based parameter vectors. Expand
  • 110
  • 2
A method for the construction of acoustic Markov models for words
A technique for constructing Markov models for the acoustic representation of words is described. Expand
  • 62
  • 2
A statistical approach to the design of an adaptive self-normalizing silence detector
Silence detection is an important aspect of automatic speech recognition. Expand
  • 28
  • 2