US 12,351,119 B2
Systems and methods for performing commands in a vehicle using speech and image recognition
Sumit Bhattacharya, Maharashtra (IN); Jason Conrad Roche, Santa Clara, CA (US); and Niranjan Avadhanam, Saratoga, CA (US)
Assigned to NVIDIA Corporation, Santa Clara, CA (US)
Filed by NVIDIA Corporation, Santa Clara, CA (US)
Filed on Dec. 6, 2022, as Appl. No. 18/062,163.
Application 18/062,163 is a continuation of application No. 16/867,395, filed on May 5, 2020, granted, now 11,590,929.
Prior Publication US 2023/0095988 A1, Mar. 30, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G10L 15/22 (2006.01); B60R 16/037 (2006.01); B60R 25/01 (2013.01); B60R 25/25 (2013.01); B60R 25/30 (2013.01); G05B 13/02 (2006.01); G06F 21/32 (2013.01); G06N 3/08 (2023.01); G06V 10/25 (2022.01); G06V 20/59 (2022.01); G10L 17/00 (2013.01); G10L 17/06 (2013.01); G10L 17/18 (2013.01)
CPC B60R 16/0373 (2013.01) [B60R 25/01 (2013.01); B60R 25/257 (2013.01); B60R 25/305 (2013.01); G05B 13/027 (2013.01); G06F 21/32 (2013.01); G06N 3/08 (2013.01); G06V 10/25 (2022.01); G06V 20/59 (2022.01); G10L 17/00 (2013.01); G10L 17/06 (2013.01); G10L 17/18 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving audio data generated using one or more microphones of a machine, the audio data representative of user speech from a first occupant of the machine;
processing the audio data to determine that the user speech from the first occupant indicates an identifier of a second occupant of the machine and an operation associated with a component of the machine, the second occupant being different than the first occupant;
receiving image data generated using one or more image sensors of the machine, the image data representative of an image depicting at least a portion of an interior of the machine;
based at least on the user speech from the first occupant indicating the identifier of the second occupant, determining, using at least the image data, that the image depicts the second occupant within a region of the machine that is associated with the component; and
causing the operation to be performed with respect to the component.