A Maximum-entropy Solution to the Frame-dependency Problem in Speech Recognition (2001)
| Citations: | 5 - 0 self |
BibTeX
@TECHREPORT{Horn01amaximum-entropy,
author = {Kevin S. Van Horn},
title = {A Maximum-entropy Solution to the Frame-dependency Problem in Speech Recognition},
institution = {},
year = {2001}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
The HMM assumption of conditional independence of observations causes a variety of problems for speech-recognition applications. Previous attempts to construct acoustic models that remove this assumption have suffered from a significant increase in the number of parameters to train. Another weakness of current acoustic models is that they do not account for the origin of derived features (estimated derivatives). We show how to both remove the independence assumption and properly account for derived features, with little or no increase in the number of parameters to train, by applying the principle of maximum entropy. We also show that ignoring the origins of derived features in training HMM acoustic models can lead to severe distortions of the effective language model. Evaluation of our maxent model on a simple problem cuts an already-low error rate in half compared to an equivalent HMM with the same number of parameters.
