Determining the origin of impulsive noise events using paired wireless sound sensors

This work investigates how to identify the source of impulsive noise events using a pair of wireless noise sensors. One sensor is placed at a known noise source, and another sensor is placed at the noise receiver. Machine learning models receive data from the two sensors and estimate whether a given noise event originates from the known noise source or another source. To avoid privacy issues, the approach uses on-edge preprocessing that converts the sound into privacy compatible spectrograms. The system was evaluated at a shooting range and explosives training facility, using data collected during noise emission testing. The combination of convolutional neural networks with cross-correlation achieved the best results. We created multiple alternative models using different spectrogram representations. The best model detected 70.8\% of the impulsive noise events and correctly predicted 90.3\% of the noise events in the optimal trade-off between recall and precision.

Automatic Detection Of Noise Events at Shooting Range Using Machine Learning

Outdoor shooting ranges are subject to noise regulations from local and national authorities. Restrictions found in these regulations may include limits on times of activities, the overall number of noise events, as well as limits on number of events depending on the class of noise or activity. A noise monitoring system may be used to track overall sound levels, but rarely provide the ability to detect activity or count the number of events, required to compare directly with such regulations. This work investigates the feasibility and performance of an automatic detection system to count noise events. An empirical evaluation was done by collecting data at a newly constructed shooting range and training facility. The data includes tests of multiple weapon configurations from small firearms to high caliber rifles and explosives, at multiple source positions, and collected on multiple different days. Several alternative machine learning models are tested, using as inputs time-series of standard acoustic indicators such as A-weighted sound levels and 1/3 octave spectrogram, and classifiers such as Logistic Regression and Convolutional Neural Networks. Performance for the various alternatives are reported in terms of the False Positive Rate and False Negative Rate. The detection performance was found to be satisfactory for use in automatic logging of time-periods with training activity.