Anomalous sound detection based on interpolation deep neural network
This work addresses labor-saving maintenance for industrial equipment, but it is incremental as it builds on existing autoencoder methods with a specific modification for non-stationary sounds.
The paper tackled the problem of detecting anomalous sounds in non-stationary industrial equipment by proposing an interpolation-based deep neural network that predicts removed frames instead of edge frames, resulting in a 27% improvement in AUC score.
As the labor force decreases, the demand for labor-saving automatic anomalous sound detection technology that conducts maintenance of industrial equipment has grown. Conventional approaches detect anomalies based on the reconstruction errors of an autoencoder. However, when the target machine sound is non-stationary, a reconstruction error tends to be large independent of an anomaly, and its variations increased because of the difficulty of predicting the edge frames. To solve the issue, we propose an approach to anomalous detection in which the model utilizes multiple frames of a spectrogram whose center frame is removed as an input, and it predicts an interpolation of the removed frame as an output. Rather than predicting the edge frames, the proposed approach makes the reconstruction error consistent with the anomaly. Experimental results showed that the proposed approach achieved 27% improvement based on the standard AUC score, especially against non-stationary machinery sounds.