公开(公告)号：US11900246B2

公开(公告)日：2024-02-13

申请号：US16914671

申请日：2020-06-29

Applicant: Samsung Electronics Co., Ltd.

Inventor： Dohwan Lee ,  Kyuhong Kim ,  Jaejoon Han

IPC: G06N3/08 ,  G06V10/82 ,  G06V40/16 ,  G06F18/40 ,  G06F18/214 ,  G06F18/2413 ,  G06F18/23213

CPC classification number: G06N3/08 ,  G06F18/214 ,  G06F18/23213 ,  G06F18/2413 ,  G06F18/41 ,  G06V10/82 ,  G06V40/168

Abstract: An on-device training-based user recognition method includes performing on-device training on a feature extractor based on reference data corresponding to generalized users and user data, determining a registration feature vector based on an output from the feature extractor in response to the input of the user data, determining a test feature vector based on an output from the feature extractor in response to an input of test data, and performing user recognition on a test user based on a result of comparing the registration feature vector to the test feature vector.

公开(公告)号：US11367451B2

公开(公告)日：2022-06-21

申请号：US16519757

申请日：2019-07-23

Applicant: Samsung Electronics Co., Ltd.

Inventor： Kyuhong Kim ,  Insoo Kim ,  Dohwan Lee ,  Hana Lee

IPC: G10L17/04 ,  G10L17/00 ,  G10L15/16 ,  G06N3/04

Abstract: A speaker authentication method and apparatus may extract input speaker features corresponding to a plurality of frames of an input speech of an object, estimate discriminable speaker sections corresponding to the plurality of frames, and dynamically match the input speaker features to pre-enrolled enrolled speaker features based on the discriminable speaker section.

公开(公告)号：US11775851B2

公开(公告)日：2023-10-03

申请号：US16545095

申请日：2019-08-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Dohwan Lee ,  Kyuhong Kim ,  Chang Kyu Choi

IPC: G06N7/01 ,  G06F21/31 ,  G06F18/214 ,  G06N3/08 ,  G06F18/2411

CPC classification number: G06N7/01 ,  G06F18/214 ,  G06F18/2411 ,  G06F21/31 ,  G06N3/08

Abstract: A user verification method and apparatus using a generalized user model is disclosed, where the user verification method includes generating a feature vector corresponding to a user based on input data corresponding to the user, determining a first parameter indicating a similarity between the feature vector and an enrolled feature vector enrolled for user verification, determining a second parameter indicating a similarity between the feature vector and a user model corresponding to generalized users, and verifying the user based on the first parameter and the second parameter.