Methods of Combining Multiple Classifiers with Different Features and Their Applications to Text-Independent Speaker Identification

Abstract

In practical applications of pattern recognition, there are often different features extracted from raw data which needs recognizing. Methods of combining multiple classifiers with different features are viewed as a general problem in various application areas of pattern recognition. In this paper, a systematic investigation has been made and possible solutions are classified into three frameworks, i.e. linear opinion pools, winner-take-all and evidential reasoning. For combining multiple classifiers with different features, a novel method is presented in the framework of linear opinion pools and a modified training algorithm for associative switch is also proposed in the framework of winner-take-all. In the framework of evidential reasoning, several typical methods are briefly reviewed for use. All aforementioned methods have already been applied to text-independent speaker identification. The simulations show that results yielded by the methods described in this paper are better than not only the individual classifiers' but also ones obtained by combining multiple classifiers with the same feature. It indicates that the use of combining multiple classifiers with different features is an effective way to attack the problem of text-independent speaker identification.

On the Combination of Logistic Regression and Local Probability Estimates

“…Another possibility is to combine the collected classifiers to construct a classifier that performs better than any of the base classifiers [10,11]. Therefore the base classifiers have to be diverse but also comparable.…”

A visual and interactive tool for optimizing lexical postcorrection of OCR results

“…Furthermore, each suggestion v in L should have a combined confidence value that takes into account all confidence values for v in the lists L i . In the literature, combination problems of a similar abstract form have been intensively studied [4,5,18,8,12,7,1,10]. Most work on combination problems in the area of OCR recognition is devoted to the combination of symbol classifiers.…”

Learning of Neural Network with Reduced Interference – An Ensemble Approach

“…There is a need of integration of results from multiple learners in ensemble learning. Many kinds of integration schemes exist, such as voting [5], Bayes voting [8], integration method based on D-S evidence theory [1,7,23], and integration of classifiers generated from different feature subsets [3,18,19,30,31]. We will consider these in our experiments.…”