Peter V. de Souza

Learn More
We address the problem of predicting a word from previous words in a sample of text In particular we discuss n gram models based on classes of words We also discuss several statistical algorithms for assigning words to classes based on the frequency of their co occurrence with other words We nd that we are able to extract classes that have the avor of(More)
This paper is concerned with the problem of estimating the parameter values of hidden Markov word models for speech recognition. It is argued that maximum-likelihood estimation of the parameters via the forward-backward algorithm may not lead to values which maximize recognition accuracy. The paper describes an alternative estimation procedure called(More)
In a continuous speech recognition system it is important to model the context dependent variations in the pronunciations of words. In this paper we present an automatic method for modeling phonological variation using decision trees. For each phone we construct a decision tree that specifies the acoustic realization of the phone as a function of the(More)