Error Analysis of Automatic Speech Recognition Using Principal Direction Divisive Partitioning
Abstract
This paper describes an experiment performed using the Principal Direction Divisive Partitioning algorithm ( Boley, 1998 ) in order to extract linguistic word error regularities from several sets of medical dictation data. For each of six physicians, two hundred finished medical dictations aligned with their corresponding automatic speech recognition output were clustered and the results analyzed for linguistic regularities between and within clusters. Sparsity measures indicated a good fit between the algorithm and the input data. Linguistic analysis of the output clusters showed evidence of systematic word recognition error for short words, function words, words with destressed vowels, and phonological confusion errors due to telephony (recording) bandwidth interference. No qualitatively significant distinctions between clusters could be made by examining word errors alone, but the results confirmed several informally held hypotheses and suggested several avenues of further investigation, such as the examination of word error contexts.
Cite
Text
McKoskey and Boley. "Error Analysis of Automatic Speech Recognition Using Principal Direction Divisive Partitioning." European Conference on Machine Learning, 2000. doi:10.1007/3-540-45164-1_28Markdown
[McKoskey and Boley. "Error Analysis of Automatic Speech Recognition Using Principal Direction Divisive Partitioning." European Conference on Machine Learning, 2000.](https://mlanthology.org/ecmlpkdd/2000/mckoskey2000ecml-error/) doi:10.1007/3-540-45164-1_28BibTeX
@inproceedings{mckoskey2000ecml-error,
title = {{Error Analysis of Automatic Speech Recognition Using Principal Direction Divisive Partitioning}},
author = {McKoskey, David and Boley, Daniel},
booktitle = {European Conference on Machine Learning},
year = {2000},
pages = {263-270},
doi = {10.1007/3-540-45164-1_28},
url = {https://mlanthology.org/ecmlpkdd/2000/mckoskey2000ecml-error/}
}