Audio synchronization of correlated video feeds

A method for synchronizing multiple audio feeds, the method comprising:

• obtaining a plurality of audio feeds comprising a plurality of audio samples over time;
• identifying a base feed of the plurality of audio feeds and a first feed of the plurality of audio feeds;
• identifying a base segment of the base feed and a first segment of the first feed;
• after first identifying the first segment, applying different temporal offsets to the first segment to create a plurality of different time-shifted first segments associated with the time-shifted first segment, each of the plurality of time-shifted first segments corresponding to a different temporally offset from the first segment;
• determining a plurality of correlation values between the base segment and each of the plurality of different time-shifted first segments, including a separate correlation value for each time-shifted segment of the plurality of different time-shifted first segments relative to the base segment;
• identifying a particular time-shifted first segment from the plurality of different time-shifted first segments that has a corresponding highest correlation value of from the plurality of correlation values corresponding to the plurality of different time-shifted first segments;
• determining a first offset value corresponding to the particular time-shifted first segment corresponding to the highest correlation value;
• and
• synchronizing the first feed with the base feed by at least temporally offsetting the first feed by a temporal offset that is based on the determined first offset value.

One or more hardware storage device having stored thereon computer-executable instructions, the computer-executable instructions being executable by one or more processors of a computer system to cause the computer system to:

• obtain a plurality of audio feeds comprising a plurality of audio samples over time;
• identify a base feed of the plurality of audio feeds and a first feed of the plurality of audio feeds;
• identify a base segment of the base feed and a first segment of the first feed;
• after first identifying the first segment, apply different temporal offsets to the first segment to create a plurality of different time-shifted first segments associated with the time-shifted first segment, each of the plurality of time-shifted first segments corresponding to a different being temporally offset from the first segment;
• determine a plurality of correlation values between the base segment and each of the plurality of different time-shifted first segments, including a separate correlation value for each time-shifted segment of the plurality of different time-shifted first segments relative to the base segment;
• identify a particular time-shifted first segment from the plurality of different time-shifted first segments that has a corresponding highest correlation value of the plurality of correlation values corresponding to the plurality of different time-shifted first segments;
• determine a first offset value corresponding to the particular time-shifted first segment corresponding to the highest correlation value;
• and
• synchronize the first feed with the base feed by at least temporally offsetting the first feed by a temporal offset that is based on the determined first offset value.