Speech Emotion Recognition With TGI+.2 Classifier

We have adapted a classification approach coming from optical character recognition research to the task of speech emotion recognition. The classification approach enjoys the representational power of a syntactic method and efficiency of statistical classification. The syntactic part implements a tree grammar inference algorithm. We have extended this part of the algorithm with various edit costs to penalise more important features with higher edit costs for being outside the interval, which tree automata learned at the inference stage. The statistical part implements an entropy based decision tree (C4.5). We did the testing on the Berlin database of emotional speech. Our classifier outperforms the state of the art classifier (Multilayer Perceptron) by 4.68% and a baseline (C4.5) by 26.58%, which proves validity of the approach.