Mesures de confiance trame-synchrone
Joseph Razik, Odile Mella, Dominique Fohr, Jean-Paul Haton.

This paper presents some confidence measures for large vocabulary speech recognition which can be evaluated directly within the first steps of the recognition process. Having some clues to drive the recognition process may help to improve the accuracy of the provided sentence. Confidence measures may fit to this goal, so we propose some measures that can help the engine as soon as possible, without having to wait for the recognition process to be completed. Furthermore, our confidence measures are local and they are based on partial word graphes. Experiments on a French broadcast news corpus are also presented and show results close to the post calculated version of the measures.