公开(公告)号：US20190206389A1

公开(公告)日：2019-07-04

申请号：US15989366

申请日：2018-05-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ki Soo KWON ,  Minyoung MUN ,  SangHyun YOO

IPC: G10L15/07 ,  G10L15/06 ,  G10L15/22

CPC classification number: G10L15/075 ,  G10L15/063 ,  G10L15/22 ,  G10L2015/0638 ,  G10L2015/225 ,  G10L2015/228

Abstract: A method and apparatus for personalizing a speech recognition model is disclosed. The apparatus may obtain feedback data that is a result of recognizing a first speech input of a user using a trained speech recognition model, determine whether to update the speech recognition model based on the obtained feedback data, and selectively update, dependent on the determining, the speech recognition model based on the feedback data.

公开(公告)号：US20210020167A1

公开(公告)日：2021-01-21

申请号：US16736895

申请日：2020-01-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ki Soo KWON ,  Jeong-Hoon PARK

IPC: G10L15/16 ,  G10L15/22 ,  G10L15/14 ,  G10L15/06 ,  G06N3/08 ,  G06N3/063

Abstract: A processor-implemented speech recognition method includes: applying, to an input layer of a neural network, a frame of a speech sequence; obtaining an output of a hidden layer of the neural network corresponding to the frame; calculating a statistical value of at least one previous output of the hidden layer corresponding to at least one previous frame of the speech sequence; normalizing the output based on the statistical value; applying the normalized output to a subsequent layer of the neural network; and recognizing the speech sequence based on the applying of the normalized output.

公开(公告)号：US20190088251A1

公开(公告)日：2019-03-21

申请号：US15916512

申请日：2018-03-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Minyoung MUN ,  SangHyun YOO ,  Young Sang CHOI ,  Ki Soo KWON ,  Hodong LEE

IPC: G10L15/06 ,  G10L15/08 ,  G10L15/187 ,  G10L15/28

Abstract: A speech signal recognition method, apparatus, and system. The speech signal recognition method may include obtaining by or from a terminal an output of a personalization layer, with respect to a speech signal provided by a user of the terminal, having been implemented by input of the speech signal to the personalization layer, the personalization layer being previously trained based on speech features of the user, implementing a global model by providing the obtained output of the personalization layer to the global model, the global model being configured to output a phonemic signal indicating a phoneme included in the speech signal through the global model being previously trained based on speech features common to a plurality of users, and re-training the personalization layer based on the phonemic signal output from the global model, where the personalization layer and the global model collectively represent an acoustic model.

公开(公告)号：US20240086684A1

公开(公告)日：2024-03-14

申请号：US18467457

申请日：2023-09-14

Applicant: Samsung Electronics Co., Ltd. ,  NEW YORK UNIVERSITY

Inventor： Ki Soo KWON ,  Kyunghyun CHO ,  Hoshik LEE

IPC: G06N3/0455 ,  G06F16/23

CPC classification number: G06N3/0455 ,  G06F16/2365

Abstract: An electronic device includes one or more processors and a memory storing instructions configured to, when executed by the one or more processors, cause the one or more processors to: implement a machine learning-based conditional generative model configured to reconstruct target data from latent vectors, the conditional generative model trained based on an existing data set for a target task; determine an extrapolation weight; generate an augmented latent vector and augmented condition data by extrapolating, based on the extrapolation weight, from a latent vector corresponding to the existing dataset and from existing condition data corresponding to the existing dataset; and generate a new dataset comprising augmented target data generated by the conditional generative model based on the augmented condition data and based on the augmented latent vector.

公开(公告)号：US20210287663A1

公开(公告)日：2021-09-16

申请号：US17337571

申请日：2021-06-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ki Soo KWON ,  Minyoung MUN ,  SangHyun YOO

IPC: G10L15/07 ,  G10L15/06 ,  G10L15/22 ,  G10L15/32

Abstract: A method and apparatus for personalizing a speech recognition model is disclosed. The apparatus may obtain feedback data that is a result of recognizing a first speech input of a user using a trained speech recognition model, determine whether to update the speech recognition model based on the obtained feedback data, and selectively update, dependent on the determining, the speech recognition model based on the feedback data.

公开(公告)号：US20210110273A1

公开(公告)日：2021-04-15

申请号：US16844534

申请日：2020-04-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ki Soo KWON ,  Hoshik LEE

IPC: G06N3/08 ,  G06F17/18 ,  G06N3/04

Abstract: A processor-implemented model training method and apparatus are provided. The method calculates an entropy of each of a plurality of previously trained models based on training data, selects a previously trained model from the plurality of previously trained models based on the calculated entropy, and trains a target model, distinguished from the plurality of previously trained models, based on the training data and the selected previously trained model.

公开(公告)号：US20200074986A1

公开(公告)日：2020-03-05

申请号：US16351612

申请日：2019-03-13

Applicant: Samsung Electronics Co., Ltd.

Inventor： Ki Soo KWON

IPC: G10L15/07 ,  G10L15/06 ,  G10L15/16 ,  G10L15/14 ,  G06N3/08

Abstract: A processor-implemented method of personalizing a speech recognition model includes: obtaining statistical information of first scaling vectors combined with a base model for speech recognition; obtaining utterance data of a user; and generating a personalized speech recognition model by modifying a second scaling vector combined with the base model based on the utterance data of the user and the statistical information.