公开(公告)号：US20230076073A1

公开(公告)日：2023-03-09

申请号：US17986000

申请日：2022-11-14

Applicant: Samsung Electronics Co., Ltd.

Inventor： Min-Joong LEE

IPC: G10L15/16 ,  G10L15/197 ,  G10L15/22 ,  G06N3/04 ,  G06N3/08

Abstract: A speech recognition method includes adding a preset special sequence to a front end of an input sequence that corresponds to an input utterance of a speaker, recognizing the preset special sequence and the input sequence, and recognizing the input sequence based on the preset special sequence and a speech recognition result obtained by recognizing the preset special sequence and the input sequence.

公开(公告)号：US20220301578A1

公开(公告)日：2022-09-22

申请号：US17511900

申请日：2021-10-27

Applicant: Samsung Electronics Co., Ltd.

Inventor： Jinwoo PARK ,  Min-Joong LEE ,  Jihyun LEE ,  Hoshik LEE

IPC: G10L21/04 ,  G10L19/04 ,  G10L15/22 ,  G10L25/30 ,  G06N3/04

Abstract: A decoding method, the method including: receiving an input sequence corresponding to an input speech at a current time; and in a neural network (NN) for speech recognition, generating an encoded vector sequence by encoding the input sequence, determining reuse tokens from candidate beams of two or more previous times by comparing the candidate beams of the previous times, and decoding one or more tokens subsequent to the reuse tokens based on the reuse tokens and the encoded vector sequence.

公开(公告)号：US20200320983A1

公开(公告)日：2020-10-08

申请号：US16787701

申请日：2020-02-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Min-Joong LEE

IPC: G10L15/16 ,  G10L15/22 ,  G10L15/197 ,  G06N3/04 ,  G06N3/08

Abstract: A speech recognition method includes adding a preset special sequence to a front end of an input sequence that corresponds to an input utterance of a speaker, recognizing the preset special sequence and the input sequence, and recognizing the input sequence based on the preset special sequence and a speech recognition result obtained by recognizing the preset special sequence and the input sequence.

公开(公告)号：US20200090642A1

公开(公告)日：2020-03-19

申请号：US16385047

申请日：2019-04-16

Applicant: Samsung Electronics Co., Ltd.

Inventor： Min-Joong LEE

IPC: G10L15/16 ,  G10L15/04 ,  G10L15/02

Abstract: A processor-implemented speech recognition method includes: extracting a speech feature from an input speech to be recognized; estimating a first sequence of first subwords corresponding to at least one portion of the input speech based on the extracted speech feature; converting the first sequence to a second sequence of at least one second subword by combining at least two of the first subwords; and recognizing the input speech by recognizing a remaining portion of the input speech based on the second sequence.

公开(公告)号：US20210358493A1

公开(公告)日：2021-11-18

申请号：US17064879

申请日：2020-10-07

Applicant: Samsung Electronics Co., Ltd.

Inventor： Min-Joong LEE

IPC: G10L15/22 ,  G10L15/02

Abstract: A processor-implemented utterance time estimation method includes: determining a plurality of attention weight matrices using an attention-based sequence-to-sequence model; selecting an attention weight matrix from the plurality of attention weight matrices; and estimating an utterance time corresponding to an output sequence based on the selected attention weight matrix.

公开(公告)号：US20210109752A1

公开(公告)日：2021-04-15

申请号：US16812600

申请日：2020-03-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Tae Gyoon KANG ,  Min-Joong LEE

IPC: G06F9/30 ,  G06F17/16 ,  G06N3/08 ,  G06F40/42

Abstract: A processor implemented natural language processing method and apparatus are provided. The natural language processing method includes converting a natural language phrase into a token vector, calculating a repetition count of the token vector, and generating an input vector by encoding the token vector based on the calculated repetition count and a position of the token vector.

公开(公告)号：US20200152180A1

公开(公告)日：2020-05-14

申请号：US16388930

申请日：2019-04-19

Applicant: Samsung Electronics Co., Ltd.

Inventor： Min-Joong LEE

IPC: G10L15/16 ,  G06F17/27

Abstract: A processor-implemented decoding method in a first neural network is provided. The method predicts probabilities of candidates of an output token based on at least one previously input token, determines the output token among the candidates based on the predicted probabilities; and determines a next input token by selecting one of the output token and a pre-defined special token based on a determined probability of the output token.

公开(公告)号：US20210366501A1

公开(公告)日：2021-11-25

申请号：US17109490

申请日：2020-12-02

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Min-Joong LEE

IPC: G10L21/02 ,  G10L25/30 ,  G06N3/08

Abstract: A method and apparatus for improving the quality of an attention-based sequence-to-sequence model. The method includes determining an output sequence corresponding to an input sequence based on an attention-based sequence-to-sequence model, selecting at least one target attention head from among a plurality of attention heads, detecting at least one error output token among output tokens constituting the output sequence based on the target attention head, and correcting the output sequence based on the error output token.

公开(公告)号：US20190172466A1

公开(公告)日：2019-06-06

申请号：US16108717

申请日：2018-08-22

Applicant: Samsung Electronics Co., Ltd.

Inventor： Min-Joong LEE ,  Hodong LEE

IPC: G10L15/30 ,  G06F17/28 ,  G06F17/27 ,  G10L15/16 ,  G06N3/08

Abstract: A language processing method and apparatus is disclosed. A language processing apparatus using a neural network may obtain context information from a source text using a neural network-based encoder, generate a prefix token from the context information using a neural network-based main decoder, generate a token sequence including at least two successive tokens sequentially following the prefix token using a skip model in response to the prefix token satisfying a preset condition, and indicate a target text in which the prefix token and the token sequence are combined as an inference result with respect to the source text.

公开(公告)号：US20180373704A1

公开(公告)日：2018-12-27

申请号：US15975927

申请日：2018-05-10

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Min-Joong LEE ,  YoungSang CHOI

IPC: G06F17/28 ,  G06N3/08

CPC classification number: G06F17/289 ,  G06F17/2845 ,  G06F17/2854 ,  G06F17/2863 ,  G06F17/2881 ,  G06N3/0454 ,  G06N3/08

Abstract: A machine translation method and a machine translation apparatus using a neural network model are provided. The machine translation apparatus extracts information associated with a keyword from a source sentence, obtains a supplement sentence associated with the source sentence based on the extracted information associated with the keyword, acquires a first vector value from the source sentence and a second vector value from the supplement sentence using neural network model-based encoders, and outputs a target sentence corresponding to a translation of the source sentence based on any one or any combination of the first vector value and the second vector value using a neural network model-based decoder.