System and method for gunshot detection

A method, comprising:

• receiving, by one or more processors, a set of audio data from each of a plurality of microphones;
• executing, by the one or more processors, one or more sound detection machine learning models using each of the sets of audio data as input to determine whether the set of audio data corresponds to an actionable sound, each set of audio data comprising a plurality of sounds;
• responsive to determining at least one set of audio data corresponds to the actionable sound, executing, by the one or more processors, a time detection machine learning model using the at least one set of audio data as input to determine each instance and time of the actionable sound;
• and
• responsive to determining each instance and time of the actionable sound, determining, by the one or more processors, a location of the actionable sound based on the time of each instance of the actionable sound in each of the at least one set of audio data.