In the context of large vocabulary speech recognition system, its of major interest to classify every utterance as being correctly or incorrectly recognised. In this paper we are presenting a preliminary study on a wordlevel confidence estimation system based on the output of a neural network. We use a combination of multiple features extracted from the acoustical and lexical decoders of our reference system, those available in the hypothesis stage of a hypothesis-verification very large vocabulary telephone speech recognition system. We will show the system architecture, describe the experiments leading to the selection of the set of parameters to be used by the NN and the final performance, showing promising results as compared with the use of standard log-likelihood ratio techniques for confidence scoring.
Cite as: Macías-Guarasa, J., Ferreiros, J., San-Segundo, R., Montero, J.M., Pardo, J.M. (2000) Acoustical and lexical based confidence measures for a very large vocabulary telephone speech hypothesis-verification system. Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000), vol. 4, 496-499, doi: 10.21437/ICSLP.2000-857
@inproceedings{maciasguarasa00b_icslp,
author={Javier Macías-Guarasa and Javier Ferreiros and Ruben San-Segundo and Juan Manuel Montero and Juan Manuel Pardo},
title={{Acoustical and lexical based confidence measures for a very large vocabulary telephone speech hypothesis-verification system}},
year=2000,
booktitle={Proc. 6th International Conference on Spoken Language Processing (ICSLP 2000)},
pages={vol. 4, 496-499},
doi={10.21437/ICSLP.2000-857}
}