In this paper we present and compare several confidence mea-sures for large vocabulary continuous speech recognition. We show that posterior word probabilities computed on word graphs and N-best lists clearly outperform non-probabilistic confidence measures, e.g. the acoustic stability and the hypothesis density. In addition, we prove that the estimation of posterior word prob-abilities on word graphs yields better results than their estimation on N-best lists and discuss both methods in detail. We present experimental results on three different corpora, the English NAB 94 20k development corpus, the German VERBMOBIL 96 evaluation corpus and a Dutch corpus, which has been recorded with a train timetable information system in the ARISE project.
Cite as: Wessel, F., Macherey, K., Ney, H. (1999) A comparison of word graph and n-best list based confidence measures. Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999), 315-318, doi: 10.21437/Eurospeech.1999-82
@inproceedings{wessel99_eurospeech,
author={Frank Wessel and Klaus Macherey and Hermann Ney},
title={{A comparison of word graph and n-best list based confidence measures}},
year=1999,
booktitle={Proc. 6th European Conference on Speech Communication and Technology (Eurospeech 1999)},
pages={315--318},
doi={10.21437/Eurospeech.1999-82}
}