Analysis of Confusion Matrix to Combine Evidence for Phoneme Recognition

In this work we analyze and combine evidences from different classifiers for phoneme recognition using information from the confusion matrices. Speech signals are processed to extract the Perceptual Linear Prediction (PLP) and Multi-RASTA (MRASTA) features. Neural network classifiers with different architectures are built using these features. The classifiers are analyzed using their confusion matrices. The motivation behind this analysis is to come up with some objective measures which indicate the complementary nature of information in each of the classifiers. These measures are useful for combining a subset of classifiers. The classifiers can be combined using different combination schemes like product, sum, minimum and maximum rules. The significance of the objective measures is demonstrated in terms the results of combination. Classifiers selected through the proposed objective measures seem to provide the best performance.

Related material