US 12,283,187 B2
Emergency response vehicle detection for autonomous driving applications
Ambrish Dantrey, Pune (IN); Atousa Torabi, Santa Clara, CA (US); Anshul Jain, San Jose, CA (US); Ram Ganapathi, San Jose, CA (US); Abhijit Patait, Pune (IN); Revanth Reddy Nalla, Maharashtra (IN); and Niranjan Avadhanam, Saratoga, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Sep. 6, 2023, as Appl. No. 18/462,287.
Application 18/462,287 is a continuation of application No. 16/951,224, filed on Nov. 18, 2020, granted, now 11,816,987.
Prior Publication US 2023/0410650 A1, Dec. 21, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G08G 1/0965 (2006.01); G06N 3/048 (2023.01); G08G 1/0967 (2006.01); H04R 3/00 (2006.01)
CPC G08G 1/0965 (2013.01) [G06N 3/048 (2023.01); G08G 1/096708 (2013.01); H04R 3/005 (2013.01); H04R 2430/20 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
determining, using one or more neural networks and based at least on first audio data generated using one or more microphones of a machine during a first time window, one or more first probabilities associated with one or more alert types;
determining, using the one or more neural networks and based at least on second audio data generated using the one or more microphones during a second time window, one or more second probabilities associated with the one or more alert types, the first time window being offset with respect to the second time window and a portion of the second audio data including a portion of the first audio data; and
causing, based at least on the one or more first probabilities and the one or more second probabilities, the machine to perform one or more operations.