Predictive evaluation of spectrogram-based vehicle sound quality via data augmentation and explainable artificial Intelligence: Image color adjustment with brightness and contrast

[Display omitted] •Quantitative evaluation results of affective sound quality using a spectrogram-based vehicle driving sound are presented.•The engine order line, which is an interpretable feature of the spectrogram, is extracted using domain knowledge.•The data were augmented using an image color modulation method that did not damage the physical meaning of the spectrogram.•Quantitative criteria for selecting data augmentation methods using explainable artificial intelligence techniques are presented. In this study, a novel method for selecting the optimal data augmentation method in combination with explainable artificial intelligence techniques is presented. Accordingly, a convolutional neural network-based model was designed to quantitatively evaluate the affective sound quality characteristics of vehicle driving sounds, which were classified as professional knowledge. Virtual learning data were created by adjusting the color of the image to avoid damaging the physical features of the spectrogram. By implementing the explainable artificial intelligence technique, the spectrogram features were extracted using domain knowledge. In particular, the engine noise of the vehicle, which plays a significant role in determining the characteristics of the running sound of the vehicle, was selected as a physical characteristic called the engine order line in the spectrogram. The explainable artificial intelligence technique was used to select the most influential feature among those extracted from the spectrogram. By observing the changes in the selected characteristics according to the data augmentation method, an optimal data augmentation method is proposed according to each characteristic. Furthermore, an average classification accuracy of 94.22% was obtained using the proposed data augmentation method, which is an improvement of 1.55–5.55% over the existing data augmentation methods. Moreover, according to the dataset, the standard deviation of the classification accuracy was 2.13%, which yielded an optimum result.