In this paper we present a confidence measure for word alignment based on the posterior probability of alignment links. We introduce sentence alignment confidence measure and alignment link confidence measure. Based on these measures, we improve the alignment quality by selecting high confidence

This paper compares different confidence measures for the results of statistical face recognition systems. The main applications of a confidence measure are rejection of unknown people and the detection of recognition errors. Some of the confidence measures are based on the posterior probability

Multimodal fusion for identity verification has already shown great improvement compared to unimodal algorithms. In this paper, we propose to integrate confidence measures during the fusion process. We present a comparison of three different methods to generate such confidence information from

In this paper the performance of different confidence measures used for an address recognition system are evaluated. The recognition system for cursive handwritten German address words is based on Hidden Markov Models (HMMs). It is essential, that the structure of the address (name, street, city

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

The majority of alcoholics and drug addicts relapse after treatment, with many substance abusers developing a chronic relapse pattern. For this study, 43 patients, who went through a 3-week inpatient relapse prevention program, answered the Situational-Confidence Questionnaire (a measure of self

Since automatic speech recognition is error prone it is highly desirable to obtain information on the reliability of a recognition result. For many applications it is interesting to know how well a sequence of words rather than a single word was understood, for example a credit card number or a phrase specifying a time or location.

Introduction It is a standard procedure to compare new amino acid sequences to databases of proteins that have been studied already in order to find similarities in structure and function. This comparison can be sequence--sequence or sequence-- structure based. In order to compare, an alignment is performed of the target protein sequence (whose structure we are searching) with a template protein (whose structure we know). For a sequence--sequence alignment, the alignment algorithm optimizes a certain scoring function that quantifies the similarities of the amino acids at individual positions. For a sequence--structure alignment, also known as threading, usually the scoring function that is optimized is designed to capture the essence of structural similarity among proteins. These scores are supposed to be comparable between different proteins, since we want to select the template which achieves the highest alignment score to the target protein as our candidate for the structural

This paper deals with the use of confidence measure for Automatic Face Recognition (AFR). AFR is realized by the adapted Kepenecki face recognition approach based on the Gabor wavelet transform. This work is motivated by the fact that obtained recognition rate on the real-world corpus is only about

this paper, we investigate the use of confidence measures for the evaluation of pronunciation models. The confidence measures and pronunciation models are obtained from the ABBOT hybrid Hidden Markov Model/Artificial Neural Network (HMM/ANN) Large Vocabulary Continuous Speech Recognition (LVCSR