In this paper, we have conducted a comparative study on several confidence measures (CMs) for large vocabulary speech recognition. Firstly, we propose a novel high-level CM that is based on the inter-word mutual information (MI). Secondly, we experimentally investigate several popular low-level CMs, such as word posterior probabilities, N-best counting, Likelihood Ratio Testing (LRT), etc. Finally, we have studied a simple linear interpolation strategy to combine the best low-level CMs with the best high-level CMs. All of these CMs are examined in two large vocabulary ASR tasks, namely the Switchboard task and a mandarin dictation task, to verify the recognition errors in baseline recognition systems. Experimental results show: 1) the proposed MI-based CMs greatly surpass another existing high-level CMs which are based on the LSA technique; 2) Among all lowlevel CMs, word posteriori probabilities give the best verification performance; 3) When combining the word posteriori probabilities with the MI-based CMs, the equal error rate is reduced from 24.4% to 23.9% in the Switchboard task and from 17.5% to 16.2% in the mandarin dictation task.
Cite as: Guo, G., Huang, C., Jiang, H., Wang, R. (2004) A Comparative Study on Various Confidence Measures in Large Vocabulary Speech Recognition. Proc. International Symposium on Chinese Spoken Language Processing, 9-12
@inproceedings{guo04_iscslp,
author={Gang Guo and Chao Huang and Hui Jiang and RenHua Wang},
title={{A Comparative Study on Various Confidence Measures in Large Vocabulary Speech Recognition}},
year=2004,
booktitle={Proc. International Symposium on Chinese Spoken Language Processing},
pages={9--12}
}