In this paper, we address the challenging problem of detecting bearing faults from vibration signals. For this, several time- and frequency domain features have been proposed. However, these proposed features are usually evaluated on data originating from relatively simple scenarios and a significant performance loss can be observed if more realistic scenarios are considered. To overcome this, we introduce Mel Frequency Cepstral Coefficients (MFCCs) and features extracted from the Amplitude Modulation Spetrogram (AMS) as features for the detection of bearing faults. Both AMS and MFCCs were originally introduced in the context of audio signal processing but it is demonstrated that a significantly improved classification performance can be obtained using the proposed features. Furthermore, the data imbalance problem that is prevailing in the context of bearing fault detection, meaning that typically much more data from healthy bearings than from damaged bearings is available. Therefore, we propose to train a One-class SVM with data from healthy bearings only. Bearing faults are then classified by the detection of outliers. Our approach is evaluated with data measured in a highly challenging scenario comprising a state-of-the-art commuter railway engine which is supplied by an industrial power converter and attached to a gear and load.