Figure 9.

Generalization of the classification. In this figure, the classifiers were trained with the reliable neurons and tested on the rest of the population. All tested combinations (1–15) based on four types of descriptors (TFRP, signal, masker, and signal/masker) of the categories in stationary and chorus noise and their respective percentages of accuracy of the classifier. The gray part means that the descriptor is included in the classifier and the white part means that the descriptor is excluded from the classifier.