US 12,112,736 B2
Apparatus, system, and method of neural-network (NN) based active acoustic control (AAC)
Tzvi Fridman, Nes Tziona (IL); Yochai Edlitz, Yavne (IL); Noam Bar, Givatayim (IL); and Mordehay Elbaz, Tel Aviv (IL)
Assigned to SILENTIUM LTD., Nes Ziona (IL)
Filed by SILENTIUM LTD., Nes Ziona (IL)
Filed on Jun. 27, 2023, as Appl. No. 18/215,055.
Claims priority of provisional application 63/356,395, filed on Jun. 28, 2022.
Prior Publication US 2024/0161725 A1, May 16, 2024
Int. Cl. G10K 11/178 (2006.01)
CPC G10K 11/17823 (2018.01) [G10K 11/17825 (2018.01); G10K 11/17881 (2018.01); G10K 2210/12821 (2013.01); G10K 2210/3026 (2013.01); G10K 2210/3027 (2013.01); G10K 2210/3038 (2013.01); G10K 2210/3046 (2013.01); G10K 2210/3055 (2013.01); G10K 2210/506 (2013.01)] 22 Claims
OG exemplary drawing
 
1. An apparatus comprising:
an input to receive input information, the input information comprising:
Active Acoustic Control (AAC) configuration information, the AAC configuration information comprising information representing one or more parameters affecting a real-time configuration of AAC in a sound control zone; and
a plurality of noise inputs representing acoustic noise at a plurality of noise sensing locations;
a controller comprising logic and circuitry, the controller configured to process the input information to determine a sound control pattern to control sound within the sound control zone based on the plurality of noise inputs, wherein the controller comprises a Neural-Network (NN) trained to generate an NN output based on an NN input, wherein the NN input is based on the AAC configuration information, wherein the controller is configured to generate the sound control pattern based on the NN output; and
an output to output the sound control pattern to one or more acoustic transducers.