Title: Robust and Efficient Confidence Measure for Isolated Command Recognition

Authors: Gustavo Hernandez-Abrego, Xavier Menendez-Pidal, Lex Olorenshaw

Abstract: A new confidence measure for isolated command recognition is presented. It is versatile and efficient in two ways. First, it is based exclusively on the speech recognizer's output. In addition, it is robust to changes in the vocabulary, acoustic model and parameter settings. Its calculation is very simple and it is based on the computation of a pseudo-filler score from an N-best list. Performance is tested in two different command recognition applications. Finally, it is efficient to separate the correct results both from the incorrect ones and from the false alarms caused by out-of-vocabulary elements and noises.

a01gh108.ps a01gh108.pdf