Human Acoustic Events Detection as Anomalies in Industrial Environments Using Shallow Unsupervised Techniques

The computational analysis of environmental sounds has garnered considerable attention in recent years, with a wide range of applications spanning media retrieval, hearing assistance, and biomonitoring systems. The two main tasks in this topic are acoustic scene classification and sound event detection. Current work presents the preliminary results of our first study of human spontaneous event identifications in real environments. The research will tackle the problem as an anomaly detection challenge, exploring the performance of semi-supervised and unsupervised shallow machine learning techniques on our sound datasets. Two sets of anomaly detection datasets have been created using our method of dataset fusion, combining a variety of acoustic scenes collected from a free sound library, as well as from different locations of our own real industrial company, and spontaneous human acoustic events from another free sound library. In addition, each dataset has been created following 7 Signal-Noise Ratio (SNR) challenges from -30dB up to +30dB, indicating that the semi-supervised algorithm Xtreme Boosting Based Outlier Detection, with 50% correctly labelled anomalies, has outperformed the rest of the algorithms across all datasets up to SNR -10dB, achieving an acceptable F1-macro score above 0.80.