US 12,068,001 B2
Acoustic event detection
Harshavardhan Sundar, Medford, MA (US); Sheetal Laad, Lexington, MA (US); Jialiang Bao, Malden, MA (US); Ming Sun, Winchester, MA (US); Chao Wang, Newton, MA (US); Chungnam Chan, Westford, MA (US); Cengiz Erbas, Acton, MA (US); Mathias Jourdain, Seattle, WA (US); Nipul Bharani, Seattle, WA (US); and Aaron David Wirshba, Seattle, WA (US)
Assigned to Amazon Technologies, Inc., Seattle, WA (US)
Filed by Amazon Technologies, Inc., Seattle, WA (US)
Filed on Sep. 8, 2023, as Appl. No. 18/243,800.
Application 18/243,800 is a continuation of application No. 17/216,840, filed on Mar. 30, 2021, granted, now 11,783,850.
Prior Publication US 2024/0071407 A1, Feb. 29, 2024
Int. Cl. G10L 25/51 (2013.01); G10L 15/06 (2013.01); G10L 15/22 (2006.01); G10L 25/78 (2013.01)
CPC G10L 25/51 (2013.01) [G10L 15/063 (2013.01); G10L 15/22 (2013.01); G10L 25/78 (2013.01); G10L 2015/0635 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method, comprising:
receiving first audio data representing first audio captured by a first device;
processing the first audio data to determine the first audio represents a first instance of a first type of event corresponding to presence of a person;
receiving second audio data representing second audio captured by the first device;
processing the second audio data to determine the second audio represents a second instance of the first type of event;
determining the first instance and second instance occurred within a first window of time;
based at least in part on the first instance and second instance occurring within the first window of time, determining first output data representing aggregate event data corresponding to the first type of event; and
causing presentation of the first output data.