Previous work has demonstrated the success of statistical language models when enough training data is available, but despite that, grammar-based systems are proving the preferred choice in successful commercial systems such as HeyAnita, BeVocal and Tellme, largely due to the difficulty involved in obtaining a corpus of training data. Here we trained an SLM on data obtained using a grammar-based system and compared the performance of the two systems with regards to recognition. We also parsed the output of the SLM using a robust parser and compared the accuracy of the semantic output of the systems. The SLM/robust parser showed considerable improvement on unconstrained input, and similar precision/recall (per slot value) on utterances provided by trained users.
Cite as: Knight, S., Gorrell, G., Rayner, M., Milward, D., Koeling, R., Lewin, I. (2001) Comparing grammar-based and robust approaches to speech understanding: a case study. Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001), 1779-1782, doi: 10.21437/Eurospeech.2001-420
@inproceedings{knight01_eurospeech,
author={Sylvia Knight and Genevieve Gorrell and Manny Rayner and David Milward and Rob Koeling and Ian Lewin},
title={{Comparing grammar-based and robust approaches to speech understanding: a case study}},
year=2001,
booktitle={Proc. 7th European Conference on Speech Communication and Technology (Eurospeech 2001)},
pages={1779--1782},
doi={10.21437/Eurospeech.2001-420}
}