公开(公告)号：US20230171543A1

公开(公告)日：2023-06-01

申请号：US17993666

申请日：2022-11-23

Applicant: SAMSUNG ELECTRONICS CO, LTD.

Inventor： Pawel DANILUK ,  Jakub TKACZUK ,  Mateusz MATUSZEWSKI

IPC: H04R3/04

CPC classification number: H04R3/04 ,  H04R2420/07

Abstract: A method of processing an audio signal includes: obtaining an audio signal; transmitting the obtained audio signal to an external electronic device; receiving, from the external electronic device, second information for adjusting a third artificial intelligence model configured to process an audio signal in real time; inputting the received second information and the obtained audio signal to the third artificial intelligence model to adjust the third artificial intelligence model; inputting the obtained audio signal to the adjusted third artificial intelligence model to obtain a processed audio signal; and reproducing the processed audio signal.

公开(公告)号：US20230419114A1

公开(公告)日：2023-12-28

申请号：US18466469

申请日：2023-09-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Krzysztof ARENDT ,  Grzegorz STEFANSKI ,  Piotr MASZTALSKI ,  Artur SZUMACZUK ,  Jakub TKACZUK ,  Mateusz MATUSZEWSKI ,  Michal SWIATEK ,  Tymoteusz OLENIECKI

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: An electronic apparatus is provided. The electronic apparatus includes a memory and a processor, wherein the processor is configured to, by executing the at least one instruction, acquire a plurality of training data; acquire a plurality of embedding vectors that are mappable to an embedding space for the plurality of training data, respectively; train an artificial intelligence model classifying the plurality of training data based on the plurality of embedding vectors, identify an embedding vector misclassified by the artificial intelligence model among the plurality of embedding vectors, identify an embedding vector closest to the misclassified embedding vector in the embedding space, acquire a synthetic embedding vector corresponding to a path connecting the misclassified embedding vector to the embedding vector closest to the misclassified embedding vector in the embedding space, and re-train the artificial intelligence model by adding the synthetic embedding vector to the training data.

公开(公告)号：US20220148556A1

公开(公告)日：2022-05-12

申请号：US17445107

申请日：2021-08-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Zuzanna KWIATKOWSKA ,  Mateusz MATUSZEWSKI ,  Michal KOSMIDER ,  Jakub TKACZUK ,  Krzysztof RYKACZEWSKI

IPC: G10K11/178 ,  G10L25/84 ,  G10L15/16 ,  G10L15/32

Abstract: An electronic device includes a communication module, and a processor. The processor is configured to identify context information. The processor is also configured to select a specific task corresponding to the context information from among predetermined inference tasks relating to processing of an audio signal The processor is further configured to select an external electronic device, which is to process the specific task, from among external electronic devices that are establishing a communication connection to the electronic device. Additionally, the processor is configured to assign processing of the specific task to the external electronic device.