Gunshot Sound Measurement and Analysis

Abstract

Exposure to gunshot sounds can cause hearing impairments. Measuring and analyzing these sounds can improve the design of hearing protectors and can help in enacting safety regulations. Furthermore, analyzing gunshot sounds can help identify the type of gun used. This is important for determining the appropriate public safety actions when a gunshot sound is detected in a public space. In this paper, we collected acoustic data from four different guns. To capture their sound including any non-symmetric sound propagation, 27 high dynamic range pressure microphones were placed around the guns forming a polar grid pattern. Audio signals were captured at 204.8 kHz sampling rate synchronously to preserve the fidelity of the impulse nature of the gunshots. In this study, an image-based analysis method was developed to take advantage of the recent advancement of image recognition techniques. Two spectral analysis methods: Short Time Fourier Transform (STFT) or Continuous Wavelet Transform (CWT), were then applied to get the spectrogram of the gunshot audio signal. Machine learning using the k-nearest neighbor and random subspaces was used to classify these spectrograms and identify which gun did the particular gunshot originated from. Under reverberant conditions, the STFT maintained a better identification accuracy than the CWT.