We present a sound-based anomaly detection system to diagnose printer health. Also, we improve the model performance by using acoustic data augmentation. We first use the detector to extract the important acoustic information from the input printer sound. Second, we use principal component analysis to do feature extraction. Third, we feed the extracted features from the previous step into the two different anomaly detection models to evaluate the model performances. Finally, we go through the same system pipeline with different augmented training data to see whether or not acoustic data augmentation can improve the model performance.