Comparison of part-of-speech and automatically derived category-based language models for speech recognition
Lists
Only you see this
Abstract
This paper compares various category-based language models when used in conjunction with a word-based trigram by means of linear interpolation. Categories corresponding to parts-of-speech as well as automatically clustered groupings are considered. The category-based model employs variable-length n-grams and permits each word to belong to multiple categories. Relative word error rate reductions of between 2 and 7% over the baseline are achieved in N-best rescoring experiments on the Wall Street Journal corpus. The largest improvement is obtained with a model using automatically determined categories. Perplexities continue to decrease as the number of different categories is increased, but improvements in the word error rate reach an optimum.
BibTeX
@inproceedings{niesler1998comparison,
author = {Thomas Niesler and Edward W. D. Whittaker and Philip C. Woodland},
title = {{Comparison of part-of-speech and automatically derived category-based language models for speech recognition}},
booktitle = {IEEE International Conference on Acoustics, Speech and Signal Processing},
year = {1998},
doi = {10.1109/icassp.1998.674396},
}Loading related content...