公开(公告)号：US20230081796A1

公开(公告)日：2023-03-16

申请号：US17865465

申请日：2022-07-15

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Amod Ashok CHOURASIA ,  Choice Choudhary ,  Sobita Choudhary

IPC: H04R25/00 ,  H04R29/00 ,  H04R3/00

Abstract: Embodiments are directed to a method and an electronic device (100) for managing audio content delivery by an audio content delivery device (100). The method includes detecting, by the audio content delivery device (100), a buzzing sound in a user's ear during output of an audio content. The audio content delivery device (100) categorizes the buzzing sound, for example, as a subjective buzzing or an objective buzzing. Further, the audio content delivery device (100) computes a user experience score and generates a modified audio content based the user experience score. The modified audio content is based on the buzzing sound and the audio content. The audio content delivery device (100) outputs the modified audio content depending on the user experience score.

公开(公告)号：US11442579B2

公开(公告)日：2022-09-13

申请号：US17116455

申请日：2020-12-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ankit Agarwal ,  Sunil Rathour ,  Harshit Oberoi ,  Nitesh Goyal ,  Nitin Kishorbhai Tanwar ,  Vipin Khushu ,  Choice Choudhary

IPC: G06F3/041 ,  G06N20/00 ,  G06F17/18 ,  G06K9/62

Abstract: A method for accidental touch prediction using machine learning (ML) classification is provided. The method includes determining, by an electronic device, a mutual data index of a sensor data using a first ML model. Further, the method includes recognizing whether the sensor data corresponds to an object touch or a non-object touch based on the mutual data index. Further, the method includes performing, by the electronic device, one of detecting that the electronic device is in a pocket mode and providing an object touch notification on a touch screen of the electronic device in response to determining that the sensor data corresponds to the object touch, and recognizing whether the sensor data corresponds to an accidental touch or a non-accidental touch using at least one second ML model based on touch data in response to determining that the sensor data corresponds to the non-object touch.