The classification of acoustic signals is an important step in many audio signal processing algorithms, e.g. in the context of speech enhancement, speech recognition, and others. Signals which are captured for classification are often degraded by an unknown amount of reverberation in a real environment. If a classifier is trained on clean and anechoic data, a mismatch between training and test conditions results in a reduced classification accuracy. In this paper, we introduce a novel equalization gain matrix which can be applied to modulation domain audio features. This gain is designed to counteract the modifications which originate from reverberation such that the mismatch between clean training data and degraded test data is reduced. Experiments show that the classification accuracy can be increased significantly for reverberant signals.