Acoustical and lexical based confidence measures for a very large vocabulary telephone speech hypothesis-verification system

In the context of large vocabulary speech recognition system, it’s 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.