US 12,089,027 B2
Automatic spatial calibration for a loudspeaker system using artificial intelligence and nearfield response
Adrian Celestinos Arroyo, Valencia, CA (US); and Victor Manuel Chin Lopez, Tijuana (MX)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on May 10, 2023, as Appl. No. 18/195,879.
Application 18/195,879 is a continuation of application No. 17/558,380, filed on Dec. 21, 2021, granted, now 11,689,875.
Claims priority of provisional application 63/226,654, filed on Jul. 28, 2021.
Prior Publication US 2023/0362569 A1, Nov. 9, 2023
Int. Cl. H04S 7/00 (2006.01); G06N 3/04 (2023.01); G06N 3/08 (2023.01); H04R 5/02 (2006.01); H04R 5/04 (2006.01); H04S 3/00 (2006.01)
CPC H04S 7/301 (2013.01) [G06N 3/04 (2013.01); G06N 3/08 (2013.01); H04R 5/02 (2013.01); H04R 5/04 (2013.01); H04S 3/008 (2013.01); H04S 2400/01 (2013.01); H04S 2400/13 (2013.01); H04S 2400/15 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A method comprising:
obtaining training data comprising one or more measured data sets captured using a plurality of microphones at a listening area;
augmenting the training data with one or more simulated data sets, wherein each simulated data set comprises measurements obtained using simulation of propagation delays;
training a machine learning model based on the training data; and
providing the machine learning model to an electronic device, wherein audio reproduced by one or more loudspeakers integrated in or connected to the electronic device is automatically spatially calibrated using the machine learning model.