US 12,014,750 B2
Audio analysis of body worn camera
Tejas Shastry, Chicago, IL (US); Svyatoslav Vergun, Morton Grove, IL (US); Colin Brochtrup, Chicago, IL (US); and Matthew Goldey, Zionsville, IN (US)
Assigned to TRULEO, INC., New York, NY (US)
Filed by TRULEO, INC., Chicago, IL (US)
Filed on Mar. 8, 2023, as Appl. No. 18/180,652.
Application 18/180,652 is a continuation of application No. 17/553,482, filed on Dec. 16, 2021.
Claims priority of provisional application 63/264,151, filed on Nov. 16, 2021.
Claims priority of provisional application 63/143,538, filed on Jan. 29, 2021.
Claims priority of provisional application 63/126,368, filed on Dec. 16, 2020.
Prior Publication US 2023/0223038 A1, Jul. 13, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 25/57 (2013.01); G10L 15/18 (2013.01); G10L 15/26 (2006.01); G10L 17/00 (2013.01); G10L 25/87 (2013.01)
CPC G10L 25/57 (2013.01) [G10L 15/1815 (2013.01); G10L 15/26 (2013.01); G10L 17/00 (2013.01); G10L 25/87 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method of using machine natural language processing to analyze language in transcribed camera footage comprising:
extracting at least one audio segment from a body camera video track;
detecting voice activity to identify starting and ending timestamps of voice;
transcribing the at least one audio segment;
identifying audio of at least one speaker;
separating the audio of the at least one speaker;
scoring the audio of the at least one speaker after separation to identify interactions of interest;
wherein a voice detection model is used to analyze the at least one audio segment to identify the starting and ending timestamps of voice; and,
wherein each word in the at least one audio segment is assigned a start and stop time.