Structured Language Modeling For Speech Recognition Errata (1999)
| Venue: | Readings in Speech Recognition |
| Citations: | 302 - 3 self |
BibTeX
@INPROCEEDINGS{Chelba99structuredlanguage,
author = {Ciprian Chelba and Frederick Jelinek},
title = {Structured Language Modeling For Speech Recognition Errata},
booktitle = {Readings in Speech Recognition},
year = {1999},
pages = {450--506},
publisher = {Morgan Kaufmann}
}
Years of Citing Articles
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
We present revised Wall Street Journal (WSJ) lattice rescoring experiments using the structured language model (SLM). 1 Experiments We repeated the WSJ lattice rescoring experiments reported in [1] in a standard setup. We chose to work on the DARPA'93 evaluation HUB1 test set --- 213 utterances, 3446 words. The 20kwds open vocabulary and baseline 3-gram model are the standard ones provided by NIST. As a first step we evaluated the perplexity performance of the SLM relative to that of a deleted interpolation 3-gram model trained under the same conditions: training data size 20Mwds (a subset of the training data used for the baseline 3-gram model), standard HUB1 open vocabulary of size 20kwds; both the training data and the vocabulary were re-tokenized such that they conform to the Upenn Treebank tokenization. We have linearly interpolated the SLM with the above 3-gram model: P (\Delta) = \Delta P 3gram (\Delta) + (1 \Gamma ) \Delta P SLM (\Delta) showing a 10% relative reduction ov...
Citations
No citations identified.
