公开(公告)号：US20210034821A1

公开(公告)日：2021-02-04

申请号：US16774166

申请日：2020-01-28

Applicant: Samsung Electronics Co., Ltd.

Inventor： Junhwi CHOI ,  Sanghyun YOO ,  Sangsoo LEE ,  Hoshik LEE

IPC: G06F40/30 ,  G06F3/0484 ,  G06F3/0482

Abstract: Disclosed is a dialogue management method and apparatus. The dialogue management method includes sequentially resolving an application domain to provide a service to a user, a function appropriate for an intent of a user from among functions of the application domain, and at least one slot to perform the function, adaptively determining an expression scheme of a dialogue management interface depending on a progress of the sequentially resolving, and displaying the dialogue management interface.

公开(公告)号：US20160247064A1

公开(公告)日：2016-08-25

申请号：US14833285

申请日：2015-08-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Sanghyun YOO ,  Taesup MOON

IPC: G06N3/08 ,  G06N3/063 ,  G06N99/00

CPC classification number: G06N3/08 ,  G06N3/0445 ,  G06N3/063 ,  G06N3/082 ,  G06N20/00 ,  G10L15/16 ,  G10L25/30

Abstract: Disclosed is a neural network training method and apparatus, and recognition method and apparatus. The neural network training apparatus receives data and train a neural network based on remaining hidden nodes obtained by excluding a reference hidden node from hidden nodes included in the neural network, wherein the reference hidden node maintains a value in a previous time interval until a subsequent time interval.

Abstract translation: 公开了一种神经网络训练方法和装置，以及识别方法和装置。 所述神经网络训练装置基于通过从所述神经网络中包含的隐藏节点排除参考隐藏节点而获得的剩余隐藏节点接收数据并训练神经网络，其中所述参考隐藏节点保持先前时间间隔中的值，直到后续时间 间隔。

公开(公告)号：US20230051625A1

公开(公告)日：2023-02-16

申请号：US17973452

申请日：2022-10-25

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sanghyun YOO

IPC: G10L15/22 ,  G10L15/30

Abstract: Disclosed is a method and apparatus for processing a speech. The method includes obtaining context information from a speech signal of a user using a neural network-based encoder, determining, based on the context information, attention information corresponding to a segment included in the speech signal, and recognizing, based on the attention information, the segment by decoding a portion of the context information identified as corresponding to the segment.

公开(公告)号：US20210110820A1

公开(公告)日：2021-04-15

申请号：US16797069

申请日：2020-02-21

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sanghyun YOO

IPC: G10L15/22 ,  G10L15/30

Abstract: Disclosed is a method and apparatus for processing a speech. The method includes obtaining context information from a speech signal of a user using a neural network-based encoder, determining intent information of the speech signal based on the context information, determining, based on the context information, attention information corresponding to a segment included in the speech signal, and determining, based on the attention information, a segment value of the segment by recognizing, using a decoder, a portion of the context information identified as corresponding to the segment

公开(公告)号：US20210110116A1

公开(公告)日：2021-04-15

申请号：US16822436

申请日：2020-03-18

Applicant: Samsung Electronics Co., Ltd.

Inventor： Sanghyun YOO ,  Young-Seok KIM ,  Junhwi CHOI

IPC: G06F40/30 ,  G06N20/00

Abstract: A word embedding method and apparatus and a word search method are provided, wherein the word embedding method includes training a word embedding model based on characteristic information of a chemical substance, and acquiring an embedding vector of a word representing the chemical substance from the word embedding model, wherein the word embedding model is configured to predict a context word of an input word.

公开(公告)号：US20190122654A1

公开(公告)日：2019-04-25

申请号：US16038343

申请日：2018-07-18

Applicant: Samsung Electronics Co., Ltd. ,  Universite de Montreal

Inventor： Inchul SONG ,  Junyoung CHUNG ,  Taesup KIM ,  Sanghyun YOO

IPC: G10L15/16 ,  G10L15/187 ,  G10L15/06 ,  G06N3/08

Abstract: A speech recognition method includes obtaining an acoustic sequence divided into a plurality of frames, and determining pronunciations in the acoustic sequence by predicting a duration of a same pronunciation in the acoustic sequence and skipping a pronunciation prediction for a frame corresponding to the duration.

公开(公告)号：US20210406688A1

公开(公告)日：2021-12-30

申请号：US17469590

申请日：2021-09-08

Applicant: Samsung Electronics Co., Ltd.

Inventor： Seongmin OK ,  Young-Seok KIM ,  Hwidong NA ,  Sanghyun YOO ,  Hoshik LEE ,  Junhwi CHOI

IPC: G06N3/08 ,  G06N3/04 ,  G06K9/62

Abstract: A method and computing device with classification verification is provided. A processor-implemented method includes implementing a classification neural network to generate a classification result of data input to the classification neural network by generating, with respect to the input data, intermediate hidden values of one or more hidden layers of the classification neural network, generating the classification result of the input data based on the generated intermediate hidden values, and generating a determination of a reliability of the classification result by implementing a verification neural network, input the intermediate hidden values, to generate the determination of the reliability.

公开(公告)号：US20210150155A1

公开(公告)日：2021-05-20

申请号：US16872723

申请日：2020-05-12

Applicant: Samsung Electronics Co., Ltd.

Inventor： Misuk KIM ,  Sanghyun YOO ,  Jeong-Hoon PARK ,  Jehun JEON ,  GyuBum HAN

IPC: G06F40/56 ,  H04L12/58 ,  G06F40/30 ,  G06F40/205 ,  G06F40/268 ,  G10L15/18

Abstract: A method and apparatus with natural language processing is disclosed. The method includes determining a first similarity between an input sentence of a user and a select first database query sentence and dependent on a determination that the first similarity fails to meet a first threshold, determining a second similarity between a portion of the input sentence, less than all of the input sentence, and a select second database query sentence, and in response to the second similarity meeting a second threshold, outputting a response sentence corresponding to the second database query sentence as a response to the input sentence.