Audio processing for detecting occurrences of loud sound characterized by brief audio bursts

A system for generating a highlight video based on detected audio events, comprising:

• a processor;
• and
• a memory having programming instructions stored thereon, which, when executed by the processor, performs one or more operations, comprising:
• receiving, by one or more processors, audiovisual content;
• processing, by the one or more processors, the audiovisual content to identify at least a first audio event and a second audio event, wherein the first audio event and the second audio event are identified by:
• computing a normalized magnitude for a plurality of window samples at a plurality of respective positions of a time analysis window across the audiovisual content, and
• detecting high energy audio bursts based on the computed normalized magnitudes;
• extracting a first audiovisual highlight associated with the first audio event from the audiovisual content, wherein the first audiovisual highlight includes first metadata associated with an event;
• extracting a second audiovisual highlight associated with the second audio event from the audiovisual content, wherein the second audiovisual highlight includes second metadata associated with the event;
• generating a highlight video including the first audiovisual highlight and the second audiovisual highlight;
• and
• transmitting the highlight video to a user device.

A non-transitory computer readable medium including one or more sequences of instructions that, when executed by one or more processors, causes:

• receiving, by one or more processors, audiovisual content;
• processing, by the one or more processors, the audiovisual content to identify at least a first audio event and a second audio event, wherein the first audio event and the second audio event are identified by:
• computing a normalized magnitude for a plurality of window samples at a plurality of respective positions of a time analysis window across the audiovisual content, and
• detecting high energy audio bursts based on the computed normalized magnitudes;
• extracting a first audiovisual highlight associated with the first audio event from the audiovisual content, wherein the first audiovisual highlight includes first metadata associated with an event;
• extracting a second audiovisual highlight associated with the second audio event from the audiovisual content, wherein the second audiovisual highlight includes second metadata associated with the event;
• generating a highlight video including the first audiovisual highlight and the second audiovisual highlight;
• and
• transmitting the highlight video to a user device.