Verbo-motor priming in the phonetic encoding of real and non-words

Abstract

In this paper, we propose a novel statistical language model to capture topic-related long-range dependencies. Topics are modeled in a latent variable framework in which we also derive an EM algorithm to perform a topic factor decomposition based on a segmented training corpus. The topic model is combined with a standard language model to be used for on-line word prediction. Perplexity results indicate an improvement over previously proposed topic models, which unfortunately has not translated into lower word error. 1. INTRODUCTION The goal of statistical language models is to assign probabilities to sequences of words, and their most prominent application is in speech recognition, where language models provide prior probabilities that help in disambiguating acoustically similar utterances. By virtue of the chain rule it is sufficient to estimate the probability P #w i jh i # of a word w i conditioned on the history of preceding words h i # w i,1 1 . The main challenge in language ...