Data Collection, Modeling, and Classification for Gunshot and Gunshot-like Audio Events: A Case Study

Abstract

Distinguishing between a dangerous audio event like a gun firing and other non-life-threatening events, such as a plastic bag bursting, can mean the difference between life and death and, therefore, the necessary and unnecessary deployment of public safety personnel. Sounds generated by plastic bag explosions are often confused with real gunshot sounds, by either humans or computer algorithms. As a case study, the research reported in this paper offers insight into sounds of plastic bag explosions and gunshots. An experimental study in this research reveals that a deep learning-based classification model trained with a popular urban sound dataset containing gunshot sounds cannot distinguish plastic bag pop sounds from gunshot sounds. This study further shows that the same deep learning model, if trained with a dataset containing plastic pop sounds, can effectively detect the non-life-threatening sounds. For this purpose, first, a collection of plastic bag-popping sounds was recorded in different environments with varying parameters, such as plastic bag size and distance from the recording microphones. The audio clips’ duration ranged from 400 ms to 600 ms. This collection of data was then used, together with a gunshot sound dataset, to train a classification model based on a convolutional neural network (CNN) to differentiate life-threatening gunshot events from non-life-threatening plastic bag explosion events. A comparison between two feature extraction methods, the Mel-frequency cepstral coefficients (MFCC) and Mel-spectrograms, was also done. Experimental studies conducted in this research show that once the plastic bag pop sounds are injected into model training, the CNN classification model performs well in distinguishing actual gunshot sounds from plastic bag sounds.

Enhancing Gun Detection With Transfer Learning and YAMNet Audio Classification

“…Each fold serves as the validation set once. This process is repeated k times, and the average performance over all folds is calculated to get the final accuracy [5] [14].…”

Measurements, Analysis, Classification, and Detection of Gunshot and Gunshot-like Sounds

“…[ 15 ], to develop a robust predictive model, audio samples must be of high quality. For this purpose, we have collected gunshot-like sounds in different environments [ 16 ]. Additionally, in an effort to maintain a standardization of the data used to generate the model, scaling was carried out in the cepstral domain (see Section 5.2 for details).…”

“…Taking the centroids of each class (see Figure 9 a above) and comparing the relative distances from the gunshot sounds, we arrive at the results shown in Table 4 below. In Table 4 below, it can be observed that the plastic bag pop sound is closest to that of the gunshot sound [ 16 ] (note that “feat2 ” and “feat3” is the x , y coordinate respectively of the centroids of each class (see Figure 9 a above)). Additionally shown in Table 4 below, is a comparative analysis, indicating which sound is closest to the gunshot sound in descending order, namely: plastic bag pop, door knock, door slam, and car backfire.…”

“…As noted in Figure 12 below, there is significant connectivity between the gunshot and plastic_pop sounds [ 16 ]. In addition, the doorknock_slam shows a significant amount of connectivity to the gunshot sound [ 23 , 24 , 29 , 35 , 41 ].…”

“… Images of some of the various environments used for the capture of the plastic bag popping sounds (class 8): ( a ) along glass corridor, ( b ) inside of personal dwelling, ( c ) between two buildings, ( d ) side of building, ( e ) open field and, ( f ) anechoic chamber [ 16 ]. …”