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：US20210172838A1

公开(公告)日：2021-06-10

申请号：US16768741

申请日：2018-12-19

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hodong LEE ,  Kwanghyun KOH ,  Kiyoung YANG

IPC: G01M99/00 ,  G06F17/18

Abstract: An electronic apparatus is provided. The electronic apparatus includes a storage storing error-related information of an external electronic apparatus, and a processor configured to obtain first error-related information with respect to a target time interval and second error-related information with respect to a standard time interval including the target time interval and time intervals other than the target time interval, from the storage, obtain frequency information for each number of error occurrences with respect to the target time interval based on the first error-related information and frequency information for each number of error occurrences with respect to the standard time interval based on the second error-related information, and compare the frequency information for each number of error occurrences with respect to the target time interval with the frequency information for each number of error occurrences with respect to the standard time interval to identify an error occurrence level with respect to the target time interval.

公开(公告)号：US20190251174A1

公开(公告)日：2019-08-15

申请号：US16013055

申请日：2018-06-20

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hodong LEE ,  Hoshik LEE

IPC: G06F17/28

CPC classification number: G06F17/289

Abstract: A processor-implemented machine translation method includes translating a source sentence expressed in a source language into a target language to determine a target sentence, determining, based on a reliability of the target sentence, whether the target sentence is appropriate as a translation result of the source sentence, and re-determining a target sentence corresponding to the source sentence in response to a result of the determining being that the target sentence is inappropriate as the translation result.

公开(公告)号：US20190163747A1

公开(公告)日：2019-05-30

申请号：US15947915

申请日：2018-04-09

Applicant: Samsung Electronics Co., Ltd.

Inventor： Tae Gyoon KANG ,  Hodong LEE

IPC: G06F17/28 ,  G10L15/06 ,  G06K9/62 ,  G06N3/04 ,  G06F17/16

Abstract: A language model training method and an apparatus using the language model training method are disclosed. The language model training method includes assigning a context vector to a target translation vector, obtaining feature vectors based on the target translation vector and the context vector, generating a representative vector representing the target translation vector using an attention mechanism for the feature vectors, and training a language model based on the target translation vector, the context vector, and the representative vector.

公开(公告)号：US20180166075A1

公开(公告)日：2018-06-14

申请号：US15585334

申请日：2017-05-03

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hodong LEE ,  Hoshik LEE

IPC: G10L15/22 ,  G10L15/18 ,  G10L15/02

CPC classification number: G10L15/02 ,  G10L15/20

Abstract: A method performed by a speech recognizing apparatus to recognize speech includes: obtaining a distance from the speech recognizing apparatus to a user generating a speech signal; determining a normalization value for the speech signal based on the distance; normalizing a feature vector extracted from the speech signal based on the normalization value; and performing speech recognition based on the normalized feature vector.

公开(公告)号：US20180046618A1

公开(公告)日：2018-02-15

申请号：US15450333

申请日：2017-03-06

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hodong LEE ,  Youngki PARK ,  Hwidong NA ,  Minyoung MUN ,  Inchul SONG

IPC: G06F17/28 ,  G06F17/30

CPC classification number: G06F17/2836 ,  G06F16/3344 ,  G06F17/2854 ,  G06F17/2863 ,  G06F17/289 ,  G06N3/0445 ,  G06N3/0454 ,  G06N3/063 ,  G06N3/08

Abstract: A translation method and apparatus may respectively perform or include: using one or more processors, plural different translation processes, in parallel, for a source sentence in a first language, including encoding, to generate respective feature vectors, the source sentence in each of two or more translation processes of the plural translation processes or the source sentence and a variation of the source sentence in respective translation processes of the plural translation processes, and decoding each of the respective feature vectors to generate respective plural candidate sentences in a second language; and selecting a final sentence in the second language from the respective plural candidate sentences in the second language.

公开(公告)号：US20180011843A1

公开(公告)日：2018-01-11

申请号：US15404941

申请日：2017-01-12

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hodong LEE ,  Youngki PARK ,  Sang Hyun YOO

IPC: G06F17/28 ,  G10L15/02 ,  G10L25/30

CPC classification number: G06F17/2854 ,  G06F17/2785 ,  G06F17/2818 ,  G06F17/2881 ,  G06F17/289 ,  G10L13/00 ,  G10L15/02 ,  G10L15/26 ,  G10L25/30

Abstract: Provided is an automated interpretation method, apparatus, and system. The automated interpretation method includes encoding a voice signal in a first language to generate a first feature vector, decoding the first feature vector to generate a first language sentence in the first language, encoding the first language sentence to generate a second feature vector with respect to a second language, decoding the second feature vector to generate a second language sentence in the second language, controlling a generating of a candidate sentence list based on any one or any combination of the first feature vector, the first language sentence, the second feature vector, and the second language sentence, and selecting, from the candidate sentence list, a final second language sentence as a translation of the voice signal.

公开(公告)号：US20160210551A1

公开(公告)日：2016-07-21

申请号：US14992129

申请日：2016-01-11

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hodong LEE ,  Hoshik LEE ,  Heeyoul CHOI ,  Yunhong MIN ,  Sang Hyun YOO ,  Yeha LEE ,  Jihyun LEE ,  YoungSang CHOI

IPC: G06N3/08 ,  G10L15/16 ,  G06F17/27 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06F17/27 ,  G06N3/04 ,  G06N3/0445 ,  G06N3/084 ,  G10L15/005 ,  G10L15/16 ,  G10L15/19

Abstract: A method and apparatus for training a language model, include generating a first training feature vector sequence and a second training feature vector sequence from training data. The method is configured to perform forward estimation of a neural network based on the first training feature vector sequence, and perform backward estimation of the neural network based on the second training feature vector sequence. The method is further configured to train a language model based on a result of the forward estimation and a result of the backward estimation.

Abstract translation: 一种用于训练语言模型的方法和装置，包括从训练数据生成第一训练特征向量序列和第二训练特征向量序列。 该方法被配置为基于第一训练特征向量序列执行神经网络的前向估计，并且基于第二训练特征向量序列执行神经网络的向后估计。 该方法还被配置为基于正向估计的结果和后向估计的结果来训练语言模型。

公开(公告)号：US20210110258A1

公开(公告)日：2021-04-15

申请号：US16831206

申请日：2020-03-26

Applicant: Samsung Electronics Co., Ltd.

Inventor： Hodong LEE

IPC: G06N3/08 ,  G10L15/06

Abstract: A processor-implemented method includes: using an encoder, determining, for each of a plurality of tokens included in an input sequence, a self-attention weight based on a token and one or more tokens that precede the token in the input sequence; using the encoder, determining context information corresponding to the input sequence based on the determined self-attention weights; and using a decoder, determining an output sequence corresponding to the input sequence based on the determined context information.

公开(公告)号：US20190236147A1

公开(公告)日：2019-08-01

申请号：US16030138

申请日：2018-07-09

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Hodong LEE

IPC: G06F17/28 ,  G10L15/22

CPC classification number: G06F17/2854 ,  G06F17/2836 ,  G10L15/22

Abstract: A processor-implemented machine translation method includes generating a target sentence by translating a source sentence expressed in a source language into a target language; and determining a reliability of the target sentence based on one or more generated third sentences generated by translating either one or both of the source sentence and the target sentence into a third language.