Sixth International Conference on Spoken Language Processing
(ICSLP 2000)

Beijing, China
October 16-20, 2000

Confidence Measures Based on the K-nn Probability Estimator

Fabrice Lefèvre

Laboratoire d’Informatique d’Avignon, Université d’Avignon et des Pays de Vaucluse, Avignon, France

In this paper, the use of the probabilities produced by a K-nearest neighbours (K-nn) estimator as confidence measure is investigated in an hypothesis verification post-processing scheme. The objective is to classify as correct or incorrect the outputs of a Gaussian mixture model (GMM) /HMM speech recognition system. Four confidence measures based on the Knn probability estimator are introduced. Preliminary experiments are reported and discussed on the TIMIT database.


Full Paper

Bibliographic reference.  Lefèvre, Fabrice (2000): "Confidence measures based on the k-nn probability estimator", In ICSLP-2000, vol.4, 195-197.