Robustness Issues in a Data-Driven Spoken Language Understanding System (2004)
| Venue: | In HLT/NAACL04 Workshop on Spoken Language Understanding for Conversational Systems |
| Citations: | 6 - 1 self |
BibTeX
@INPROCEEDINGS{He04robustnessissues,
author = {Yulan He and Steve Young},
title = {Robustness Issues in a Data-Driven Spoken Language Understanding System},
booktitle = {In HLT/NAACL04 Workshop on Spoken Language Understanding for Conversational Systems},
year = {2004}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Robustness is a key requirement in spoken language understanding (SLU) systems. Human speech is often ungrammatical and ill-formed, and there will frequently be a mismatch between training and test data. This paper discusses robustness and adaptation issues in a statistically-based SLU system which is entirely data-driven. To test robustness, the system has been tested on data from the Air Travel Information Service (ATIS) domain which has been artificially corrupted with varying levels of additive noise. Although the speech recognition performance degraded steadily, the system did not fail catastrophically. Indeed, the rate at which the end-to-end performance of the complete system degraded was significantly slower than that of the actual recognition component.
