Theater ears audio recognition & synchronization algorithm

Abstract

The goal of the audio recognition and synchronization algorithm is to obtain the timestamp (start) of a smaller microphone recorded audio track in a larger (original/unmodified) audio track and to synchronize with the second language track based on the timestamp retrieved. In order to get the position of recorded audio track in original track we first generate a finger print of the original audio track. Next, we run a similar process for the recorded track to generate a second finger print. Given the finger print of the original audio track and the recorded audio track (created above) we can detect the timestamp of the recorded audio track in the original audio track. This is accomplished by matching the frequencies in the finger prints and checking if these frequencies correspond in time. Finally, we apply a detection algorithm to get the timestamp.

Dependencies are inferred from the claim text.