Published in

Springer Verlag, Lecture Notes in Computer Science, p. 181-188

DOI: 10.1007/3-540-46154-x_25

Links

Tools

Export citation

Search in Google Scholar

Comparison and Combination of Confidence Measures.

Journal article published in 2002 by Georg Stemmer, Stefan Steidl, Elmar Nöth ORCID, Heinrich Niemann, Anton Batliner
This paper is available in a repository.
This paper is available in a repository.

Full text: Download

Green circle
Preprint: archiving allowed
Upload
Green circle
Postprint: archiving allowed
Upload
Red circle
Published version: archiving forbidden
Policy details
Data provided by SHERPA/RoMEO

Abstract

A set of features for word-level confidence estimation is developed. The features should be easy to implement and should require no additional knowledge beyond the information which is available from the speech recognizer and the training data. We compare a number of features based on a common scoring method, the normalized cross entropy. We also study different ways to combine the features. An artificial neural network leads to the best performance, and a recognition rate of 76% is achieved. The approach is extended not only to detect recognition errors but also to distinguish between insertion and substitution errors.