A novel confidence measure based on marginalization of jointly estimated error cause probabilities

We propose a novel confidence measure based on the marginalization of jointly estimated error cause probabilities. Conventional confidence measures directly score the reliability of recognition results. In contrast, our method first calculates joint confidence and error cause probabilities and then sums them with respect to the error cause patterns to obtain the marginal confidence probability. We show experimentally that, the confidence estimation accuracy obtained with the proposed method is significantly improved compared with that obtained with the conventional confidence measure.