This paper describes methods for evaluating automatic speech recognition (ASR) systems in comparison with human perception results, using measures derived from linguistic distinctive features. Error patterns in terms of manner, place and voicing are presented, along with an examination of confusion matrices via a distinctive-feature-distance metric. These evaluation methods contrast with conventional performance criteria that focus on the phone or word level, and are intended to provide a more detailed profile of ASR system performance,as well as a means for direct comparison with human perception results at the sub-phonemic level.
@article{arxiv.1612.03990,
title = {Evaluating Automatic Speech Recognition Systems in Comparison With Human Perception Results Using Distinctive Feature Measures},
author = {Xiang Kong and Jeung-Yoon Choi and Stefanie Shattuck-Hufnagel},
journal= {arXiv preprint arXiv:1612.03990},
year = {2016}
}