Advanced search


Roberto Paredes, Alberto Sanchis, Enrique Vidal, Alfons Juan. Utterance Verification using an Optimized k-Nearest Neighbor Classifier. Eurospeech 2003, 2003.

Utterance verification can be seen as a conventional pattern classification problem in which a feature vector is obtained for each hypothesized word in order to classify it as either correct or incorrect. In this paper, we study the application to this problem of an optimized version of the k-Nearest Neighbour decision rule. Experiments are reported showing that it gives comparative good results.