Neural-Network Based Measures of Confidence for Word Recognition


Weintraub, M., Beaufays, F., Rivlin, Z., Konig, Y., & Stolcke, A. (1997, April). Neural-network based measures of confidence for word recognition. In 1997 IEEE International Conference on Acoustics, Speech, and Signal Processing (Vol. 2, pp. 887-890). IEEE.


This paper proposes a probabilstic framework to define and evaluate confidence measures for word recognition. We describe a novel method to combine different knowledge sources and estimate the confidence in a word hypothesis, via a neural network. We also propose a measure of the joint performance of the recognition and confidence systems. The definitions and algorithms are illustrated with results on the Switchboard Corpus.

Read more from SRI